{"as_of":"2026-08-06T16:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:16337586a256982ae9a08fba9040f3d41b453df803fbfa968fe133641cc1a5dc","coverage":[{"denominator":300,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-26T14:00:19.385619Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2606.21354/citation-record","integrity":"/paper/2606.21354/integrity","json":"/paper/2606.21354/citation-record.json","paper":"/paper/2606.21354"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1093/imanum/drz031","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"IMA Journal of Numerical Analysis , volume =","venue":"IMA Journal of Numerical Analysis","work_id":"83d56acb-16a0-48cc-8364-75320c319ac4","year":2020},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:86a75e6be211fbf0ce27e9e8c3dc10fb3d64b0c45df64ab1c07821d3c15a75c9","observation_id":"f597e278-51c8-4d3e-9cad-c79ea94f0ae2","resolution":{"observed_at":"2026-06-26T14:19:31.509082Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Restarted Nonconvex Accelerated Gradient Descent: No More Polylogarithmic Factor in the in the O (epsilon\\^","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:c6326a145477b018f913566163cc401482aed6d0d55808576399c59dc1404932","observation_id":"4d6f6f6c-072d-4314-b088-6ba0cdf96e55","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.03983","last_updated":"2017-05-03T16:28:09Z","snapshot_observed_at":"2026-07-06T05:06:55.589962Z","submitted_at":"2016-08-13T13:46:05Z","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","version":5},"cited_work":{"arxiv_id":"1608.03983","doi":"10.21203/rs.3.rs-7055642/v1","metadata_source":"pith","pith_arxiv_id":"1608.03983","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","venue":"cs.LG","work_id":"ad476478-c5ea-495b-a454-168c504bbfcc","year":2016},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"cited_paper":"/paper/1608.03983","citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:eaed3edce8623373aae80c44b88596c0b8c30b7102f49464e5ff6911656c630c","observation_id":"fd2fdc87-6300-4bb6-9fb1-42a45186d0f6","resolution":{"observed_at":"2026-07-04T06:59:37.603768Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Adaptive restart of the optimized gradient method for convex optimization , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:788e854b843731e799fde74c74a2d81f824e57155f6d86a3543c42cdb4c4f2f1","observation_id":"288020d3-d210-4f25-90d9-527d936a3ef5","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Scheduled restart momentum for accelerated stochastic gradient descent , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:88007bb0fa03292e1b300a267ac154d0c63818e3d6fd6e7b4b73a21f85037088","observation_id":"c04db3ee-3300-490a-a1eb-c50d57a14b54","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.11582","last_updated":"2020-04-27T15:23:01Z","snapshot_observed_at":"2026-08-04T04:48:56.111193Z","submitted_at":"2020-02-26T16:06:27Z","title":"Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization","version":3},"cited_work":{"arxiv_id":"2002.11582","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2002.11582","snapshot_observed_at":"2026-07-04T06:59:37.584197Z","title":"arXiv preprint arXiv:2002.11582 , title =","venue":null,"work_id":"3ef28fbe-476a-4cec-867a-2cfaf0d4d382","year":2002},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"cited_paper":"/paper/2002.11582","citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:3f6c381a9b60129232db7da86f5c180c370e6ca9987f26c59a6f901288705510","observation_id":"126a9639-a55b-42a5-950d-8ba527291b59","resolution":{"observed_at":"2026-07-04T06:59:37.585605Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Rsg: Beating subgradient method without smoothness and strong convexity , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:c1500340ea98e1755530cd3c386dec4559b3a05e0892b0ce4f37199ef3acd025","observation_id":"7d2d4e2a-86bd-4c00-844b-0ca55d749f97","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Kurdyka--","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:744c8448b8fc4b17a311f75b3187e2631bafbc81fd5b751b16a6a0cb40011894","observation_id":"42ff5010-f52f-4454-9d14-da301a86431f","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Learning with gradient descent and weakly convex losses , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:8e0edc7f6b20615ab55f5676fea657a05c9c4e93e6f396fb93c8a7d0bd1e3fd5","observation_id":"2a8d2306-a18e-478c-842d-90787ecf5235","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Subgradient methods under weak convexity and tame geometry , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:045c316e80f6be18d56994fc548f2a7e52d5c96b64a628c9273a080f6181679b","observation_id":"e42436bd-6542-4072-b447-f64d9faa24e5","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"From error bounds to the complexity of first-order descent methods for convex functions , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:5fddc9cf7463bbb11b0419445ec4a4b767eefefb431b7121caf9028a1dca3a2c","observation_id":"bd917e02-67a2-43fe-aa0b-fc5b2656cd26","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward--backward splitting, and regularized Gauss--Seidel methods , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:a3249eef427c291139bd1b1adfac6fe66ab82980bddb4b13be33184d2a8c31ef","observation_id":"6c441819-a5af-4882-acb9-0599609dbecb","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Sharp analysis of stochastic optimization under global","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:d73ae58c65bbb0a7a67fbc86734453484c37e75d65f8bb1d7d55a54ef5dcfec8","observation_id":"ab58d737-2451-4571-bafd-adf1f71c57f7","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Convergence rates and approximation results for SGD and its continuous-time counterpart , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:3850c9282c3446f9f3bf00ee540b8bd74993829bcd6a2526bd279b09a1d09245","observation_id":"1b9fce25-deb8-414e-afc9-7c7da6d6a8dc","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Efficiency of minimizing compositions of convex functions and smooth maps , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:9df6adf1a6dd40aefc9c6888dd92ba1825f6e5f4ad4a19941dd8916ff3136ae9","observation_id":"bf41ce8e-4cb6-439d-b532-a973f72be590","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1712.06038","last_updated":"2017-12-17T00:54:54Z","snapshot_observed_at":"2026-07-06T06:14:42.724196Z","submitted_at":"2017-12-17T00:54:54Z","title":"The proximal point method revisited","version":1},"cited_work":{"arxiv_id":"1712.06038","doi":null,"metadata_source":"pith","pith_arxiv_id":"1712.06038","snapshot_observed_at":"2026-07-04T06:59:37.614953Z","title":"The proximal point method revisited","venue":"math.OC","work_id":"aea69cda-e1b9-4d8a-a622-b474a3999399","year":2017},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"cited_paper":"/paper/1712.06038","citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:b964352dca0f88523ffe675b0eb2c878dfca056defa5746588426a8d32dd1e8b","observation_id":"8dd00d40-a7c2-4669-815c-bc61cd2c4aa3","resolution":{"observed_at":"2026-07-04T06:59:37.616578Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.02988","last_updated":"2018-02-19T23:21:25Z","snapshot_observed_at":"2026-07-06T06:22:26.941426Z","submitted_at":"2018-02-08T18:03:12Z","title":"Stochastic subgradient method converges at the rate $O(k^{-1/4})$ on weakly convex functions","version":3},"cited_work":{"arxiv_id":"1802.02988","doi":null,"metadata_source":"pith","pith_arxiv_id":"1802.02988","snapshot_observed_at":"2026-07-04T06:59:37.545861Z","title":"Stochastic subgradient method converges at the rate $O(k^{-1/4})$ on weakly convex functions","venue":"math.OC","work_id":"98c1fdd4-5724-4e5f-bcff-36f2edf55e58","year":2018},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"cited_paper":"/paper/1802.02988","citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:b4626e13e316eab2785220e6772b33af2e29cad02813ce1b3b938b537fec7593","observation_id":"132ae4e3-5d78-4dca-9bc1-5f32f89e7e2d","resolution":{"observed_at":"2026-07-04T06:59:37.547040Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.12645","last_updated":"2025-04-08T16:47:42Z","snapshot_observed_at":"2026-07-06T20:53:31.919637Z","submitted_at":"2025-03-16T20:49:34Z","title":"Understanding Gradient Orthogonalization for Deep Learning via Non-Euclidean Trust-Region Optimization","version":2},"cited_work":{"arxiv_id":"2503.12645","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.12645","snapshot_observed_at":"2026-07-04T07:29:38.574824Z","title":"arXiv preprint arXiv:2503.12645 , year=","venue":null,"work_id":"fe62cb1b-f9dc-4379-8586-5c2f591ba7e5","year":2025},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"cited_paper":"/paper/2503.12645","citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:8a7a4c7551f1b263ffe0879c52eec53ff3f9d0beb0c52d282f7396a0ecadf0e2","observation_id":"a83a9502-bad2-4dd0-ac1c-c4ee563acc12","resolution":{"observed_at":"2026-07-04T06:59:37.581655Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.13416","last_updated":"2025-05-19T17:50:45Z","snapshot_observed_at":"2026-07-06T21:26:30.087184Z","submitted_at":"2025-05-19T17:50:45Z","title":"Gluon: Making Muon & Scion Great Again! (Bridging Theory and Practice of LMO-based Optimizers for LLMs)","version":1},"cited_work":{"arxiv_id":"2505.13416","doi":"10.48550/arxiv.2505.13416","metadata_source":"arxiv_reference","pith_arxiv_id":"2505.13416","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Gluon: Making muon & scion great again! (bridging theory and practice of lmo-based optimizers for llms).arXiv preprint arXiv:2505.13416","venue":"ArXiv.org","work_id":"2c6f1a84-0bed-4e77-b4e0-760a8296a5c9","year":2025},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"cited_paper":"/paper/2505.13416","citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:1ee83fda69a91ac48ed7754da012533dedde6c0bb7ddd510bba98b923eb9549f","observation_id":"a709a072-8953-4030-8981-52c91daf5d42","resolution":{"observed_at":"2026-07-04T06:59:37.619277Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:520f65dd72acac1d36dc62daa8b177ad2cdefe7ca514c59c74f71fb9ccaa07dc","observation_id":"a2bb2518-f6f3-4ddf-a46e-87348d34f2c6","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Automated tight Lyapunov analysis for first-order methods , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:9b7669a3dc2d7d7992e86ae749b97cf54883d5d1158d7d02a475e626c0094446","observation_id":"22bf0d79-5136-42d4-b5db-289af9be1b88","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.18282","last_updated":"2025-05-21T09:49:25Z","snapshot_observed_at":"2026-07-06T18:37:17.280637Z","submitted_at":"2024-06-26T12:08:44Z","title":"Frank-Wolfe meets Shapley-Folkman: a systematic approach for solving nonconvex separable problems with linear constraints","version":3},"cited_work":{"arxiv_id":"2406.18282","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.18282","snapshot_observed_at":"2026-07-04T06:59:37.563445Z","title":"arXiv preprint arXiv:2406.18282 , title =","venue":null,"work_id":"f0ef122f-d739-4448-a7c0-6016a0c95014","year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"cited_paper":"/paper/2406.18282","citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:0e0bf421a41eba401b62386c2927f3f91e0d1cbe2b44db03afeaa7c4ad933209","observation_id":"52a3faad-b45e-44d1-a1f8-2900456f9a0d","resolution":{"observed_at":"2026-07-04T06:59:37.564946Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Birthday paradox, coupon collectors, caching algorithms and self-organizing search , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:234baf3a6b2a040b67b407b844a4895a7a103c1f662ce4844e91a37ef9d8a5dd","observation_id":"f4bf2b5c-0751-46f4-8f68-ceffe0512c9e","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Global tracking and quantification of oil and gas methane emissions from recurrent sentinel-2 imagery , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:8e22c73dfecf3ed23da75795345ddf565ff1b81d5bf37807d2afe65bb24a50c2","observation_id":"945c014c-b9e9-47a2-b2b2-42c8433f7893","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Digital twinning of all forest and non-forest trees at national level via deep learning , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:36c6274522a84f1b7fa06c3b11a3df299e4153f34860516099fd8119f4b2e854","observation_id":"d110bdb0-9ea0-4b7d-adaf-1640a2b1920c","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"High resolution assessment of coal mining methane emissions by satellite in Shanxi, China , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:afbbaa9be69dab068fca3ad13405b6a36be269dde5208d69637d165ce4c04a88","observation_id":"a8cc37de-b6b1-4772-857f-4fae24f6636d","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Stable bounds on the duality gap of separable nonconvex optimization problems , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:6cdf9e362857969dd7d96989559b09dc7ea2d35da9d93b0bda1fb490210b6334","observation_id":"7622967f-4242-4051-a3ee-7195e8859d66","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2306.17470","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T06:59:37.597333Z","title":"arXiv preprint arXiv:2306.17470 , title =","venue":null,"work_id":"1aaf846f-2a36-45fd-9b4d-4609cfd41154","year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:0d99fc41dc46b33748608b3fb9183ce57ccef7fbb26ea9144346397b9e3c4b56","observation_id":"4ba56856-b678-4216-bcb9-4d6ecc6366f3","resolution":{"observed_at":"2026-07-04T06:59:37.598935Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":", bibtex_show =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:08b7dde8f065a8c494029ef3fe4c41193ab01c9ca64c753e0495f4991c9520c3","observation_id":"8fae45a3-45ca-41ac-94b3-231d19025b2b","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Performance estimation toolbox (PESTO): Automated worst-case analysis of first-order optimization methods , year =","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:0cc64304a6814a869676991f96b0cbe21c74a4cf8f5093169da71171fc6136de","observation_id":"b10ef3fa-bf51-48e0-9c71-33f71fb2fb91","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"and Drori, Yoel , bibtex_show =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:9c74190e22afb6a483a37d32ab9cd667d6e1568e9ec7dcea9d1153458c3704b9","observation_id":"91a4f283-a17c-4b07-b85e-3b76bda8dca3","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"and Taylor, Adrien B","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:836388dad952560190e8a5ce07df9d0fbeecf01c4ec1b22db9cee69cc8d0f6e5","observation_id":"397a81d2-155a-490a-9a4f-6173276f7042","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Worst-case convergence analysis of inexact gradient and Newton methods through semidefinite programming performance estimation , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:05b98b7833809c8ccc309c7afb7e4649fb375d3675b0c57ea017dd9397743276","observation_id":"3389b787-675f-4796-a886-c70bbd5eeead","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Exact worst-case convergence rates of the proximal gradient method for composite convex minimization , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:1f6178008a15e93b6a86f6c00646a35d542882659742f7858faa44ca2b5f01dd","observation_id":"c2701acf-78d8-4e84-a635-2671e9fc3ebe","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Exact worst-case performance of first-order methods for composite convex optimization , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:a1d68595b2d63ff9ddf8745e04c08e7bbc3587840d94a1413bc3d459f975db9e","observation_id":"dddb1a7c-f6b4-4e7c-b7be-285c12b8eb2a","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"On the worst-case complexity of the gradient method with exact line search for smooth strongly convex functions , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:cb98e07336fe287158e7333b051ee529c640fe7fc5bafb8e424da3bda0922e0f","observation_id":"658686a4-9c71-45b4-93a8-399f54fd9302","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Smooth strongly convex interpolation and exact worst-case performance of first-order methods , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:810b23342826ecdc0e9620188f8da94f0c96c024d956962b974bbf1721984778","observation_id":"2d19af0f-2ba8-48b5-a3ca-4a93305a5cbe","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"and d'Aspremont, Alexandre and Bolte, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:80a0b50938b6d74fed03e10e4aef18038043e029090cd3c84e450b1f24228e3b","observation_id":"732a0c0c-696d-4b8d-b0d2-8c2712022151","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Truncated singular value decomposition solutions to discrete ill-posed problems with ill-determined numerical rank , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:464c99b9e18620a71502fd0a4992298d1cbfab2767e3ffa8961dff6223695214","observation_id":"8b3e530f-3206-4af4-a6f0-0ef57beccc78","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:c61c3e328aca7c461e303f94d381476f1de349d6161daa107277dc9b4548768b","observation_id":"139e3567-168f-4a81-8f12-74c0f56b3c2e","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Naive feature selection: Sparsity in naive bayes , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:8ff8e7c5deb56343e50197608a001b01309710e88ea163e1cd11c93345b6dd71","observation_id":"643a6dce-1b9f-445d-b336-c9d15c8a4d34","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.06742","last_updated":"2021-02-12T19:53:15Z","snapshot_observed_at":"2026-08-06T04:47:54.096294Z","submitted_at":"2021-02-12T19:53:15Z","title":"Approximation Bounds for Sparse Programs","version":1},"cited_work":{"arxiv_id":"2102.06742","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2102.06742","snapshot_observed_at":"2026-07-04T06:59:37.620479Z","title":"arXiv preprint arXiv:2102.06742 , title =","venue":null,"work_id":"33500482-93c1-4669-923d-9a3e60a19f43","year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"cited_paper":"/paper/2102.06742","citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:fde6fc3a52df74a418158bbab2a7074cae37f634801e465534e5ac7ee7e75681","observation_id":"29d12d9c-dc70-433f-b3d6-930de4b59db9","resolution":{"observed_at":"2026-07-04T06:59:37.622204Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Asymptotic behavior of products Cp= C+...+C in locally compact abelian groups , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:946649e27e5101999a3ce93d7b0b8baa9d189569c8ef94facd377e251a0d0bba","observation_id":"29d05c42-7457-499a-b943-effea957a187","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Strong convexity of sets and functions , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:6cb53215b4fe915006a11e2f3d32ea1c197f66d49392b04e87f2c80dea0d39b2","observation_id":"f2434e43-7a49-49f3-a2a0-fad00f3936a3","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Vector extrapolation methods with applications , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:fd5cf0d8b2b63c867c82f6e05ac65e58e5f989a880fbfbc185dc0cf63d5e927a","observation_id":"e38aecc6-98ba-40e6-9c4b-5b5a3bdcfdb1","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Globally convergent type-I Anderson acceleration for nonsmooth fixed-point iterations , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:19809f2bd4110870bcbe66c4eb892b142ed4b8fd918bb4701c57fb8f1c6bff04","observation_id":"9f2b4e8e-43f3-49c0-858c-db12a463e4ec","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Anderson acceleration of the alternating projections method for computing the nearest correlation matrix , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:b813fa9b5a161c0fe238b528bf0b32eef752debefaac0d46963d5c0928639c5b","observation_id":"6802c544-b6b3-44ed-99bd-d5e59235f252","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"MiKM: multi-step inertial Krasnoselskii--Mann algorithm and its applications , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:24261d404c06c34ecd711bc8aaf71d6d23fb92ff7fa7bbd8ba6e14c1ae0f888a","observation_id":"b9910cbb-a53f-4c1b-8ebe-6ed5d707ee2e","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Quasi-nonexpansive iterations on the affine hull of orbits: from Mann's mean value algorithm to inertial methods , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:e35b201ef70bdf307274ef5a6b5d78d78e827a6d5c85e97a9b7219c7e1519e24","observation_id":"af17171f-6e19-45a3-838a-d486d62d6818","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Chebyshev acceleration techniques for solving nonsymmetric eigenvalue problems , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:59c3336bc8a6f36981a72d456715641635833005984dd0dd8cf4aca0c47e382c","observation_id":"e5182f7b-18fa-4bea-90e4-33bfa1dd5907","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Nearly optimal first-order methods for convex optimization under gradient norm measure: An adaptive regularization approach , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:5afad29a058def52daacf4e178076259c42a16ec9305978d688b9df32f0b814a","observation_id":"0711d14e-3825-4a6c-89bf-f211972c0669","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Numerical determination of fundamental modes , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:9f4b1a274775893bff9c7aaf24f9089eb4dcb91a06a521512f01c36bf6582348","observation_id":"bcb4722a-b3af-4b21-9e37-a5b4ac0bc447","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"How to make the gradients small , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:d8a2fc79003859a4a803c4074a4312194ccbf21ff50715458f1fd71af2ef8b4e","observation_id":"02c90d18-e038-4151-a32f-ccd82052c22d","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"A well-conditioned estimator for large-dimensional covariance matrices , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:9f512ff8a168a046bd94b4c17857ce301032ebab3a667afe6db506c81c9af8df","observation_id":"c5464362-00de-447c-be3f-19ae411a9615","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Why are big data matrices approximately low rank? , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:dbb4d2907a665e1f4d2498de5745369a1c8ccef82d3ff420f2996029e3afd2a0","observation_id":"35883afb-79a2-41ef-bf7a-a6829599bf29","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.09547","last_updated":"2019-07-22T19:52:11Z","snapshot_observed_at":"2026-07-06T08:09:25.854208Z","submitted_at":"2019-07-22T19:52:11Z","title":"Stochastic algorithms with geometric step decay converge linearly on sharp functions","version":1},"cited_work":{"arxiv_id":"1907.09547","doi":null,"metadata_source":"pith","pith_arxiv_id":"1907.09547","snapshot_observed_at":"2026-07-04T06:59:37.607577Z","title":"Stochastic algorithms with geometric step decay converge linearly on sharp functions","venue":"math.OC","work_id":"d29c6d96-8e12-4b44-8538-d97ec365b607","year":2019},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"cited_paper":"/paper/1907.09547","citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:23d145ba02ed6eb3592640e4cfcb4dd684acf7d0fe32c1d93ec8a06cd3db7c80","observation_id":"4f549f91-63d1-49f6-a8a3-757b93236314","resolution":{"observed_at":"2026-07-04T06:59:37.608888Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Iterative procedures for nonlinear integral equations , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:4b28973b21c5a7792c566f8af94fadd21d35e353f2e7d2916a2e1a8242283b0a","observation_id":"5f3e4b67-15b1-45ce-9882-4564d09f535e","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.15482","last_updated":"2020-10-29T10:59:39Z","snapshot_observed_at":"2026-08-04T07:56:35.108949Z","submitted_at":"2020-10-29T10:59:39Z","title":"Convergence of Constrained Anderson Acceleration","version":1},"cited_work":{"arxiv_id":"2010.15482","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2010.15482","snapshot_observed_at":"2026-07-04T06:59:37.508781Z","title":"arXiv preprint arXiv:2010.15482 , title =","venue":null,"work_id":"cbe47212-eb0c-42e5-8966-be95ce4c3902","year":2010},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"cited_paper":"/paper/2010.15482","citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:969a14c338a276e5eead432bf510746e3dbbf9638d3f58517b7c98b1b475fa18","observation_id":"e8711404-847c-4771-bb29-8846752c6f88","resolution":{"observed_at":"2026-07-04T06:59:37.510287Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Chebyshev polynomials , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:1a0aadc61952043fc2c77b178ef1ff5e4613c5ce7ec5a9044a4610d513700740","observation_id":"00bf25ee-1d6e-4811-8e09-4ab0e6ce14d5","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Hybrid deterministic-stochastic methods for data fitting , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:bf3029bf2ff0d67fceb2e9ed045eb11102f2df5aac1db860a353077c4d2038a5","observation_id":"54b155f2-a83d-42b3-9c2b-b1b5f58f1aea","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"ECOS: An SOCP solver for embedded systems , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:b2da6f27ee411908eb710ac60138c3ba67e03aa9f322969f5d95486ae58bc51b","observation_id":"63c7e3f3-e901-4080-a085-49e606400ad3","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"A Continous Exact _0 penalty (CEL0) for least squares regularized problem , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:612ce7a6ac4b2e96e46c44b52fd64aefb0cb97190b2794bb46b0241ca5e600f7","observation_id":"33519d45-2913-4633-978a-87483b7f143c","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Sinkhorn distances: Lightspeed computation of optimal transport , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:7d2123acc3f8fdced7831fe0e664dc373dddec64a20565f6f9db684e4e9a8b41","observation_id":"d5f99ae3-2279-457f-846b-34fb2de85237","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"The use of entropy maximising models, in the theory of trip distribution, mode split and route split , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:f1de725ee11eea21342ed149c4bb46be1e52dcb0331da7ad1da6c3ef87e0bb0b","observation_id":"35c6b3be-b2ea-4d17-99af-1cbc14d18545","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Wasserstein barycenter and its application to texture mixing , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:4ba510ae49ec745eaddde428c418707291080c4e66dca19c2084d23ba4f82073","observation_id":"e677f035-1a99-429a-991f-2f1ee1249d78","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Barycenters in the Wasserstein space , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:19db8d6be17e96109ac890c2f71a88107881407157d48dac4cb57c7f7d544df0","observation_id":"1ef5bd68-f262-4352-bdc3-cfbecf0f276e","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Computational Optimal Transport: With Applications to Data Science , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:94771fe12827b852acb60612332091520938fc2c5fd29c03b08f5322282be567","observation_id":"534326db-7692-41aa-8e63-b6e388079218","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"The global methane budget 2000--2017 , volume =","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:28f785ae69812352de1ea0c5425da178aefad0b3627af6913cc8ab9df0cd1e07","observation_id":"8efd81a6-37f5-4733-a2bc-faeeef7da379","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Distributed algorithms via gradient descent for fisher markets , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:5c1ebd9300c8d68b2762610ff018c02b875dc02ad8c9c81c5d55e4229a814f65","observation_id":"75a2adb6-15b9-4d58-a64b-cab3b6aa69e9","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Relatively smooth convex optimization by first-order methods, and applications , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:9eacc8888037ff68e77ce3e303a66a56447a936e896a44b11ee194aab6da6b2b","observation_id":"50dc1314-7314-437b-bf7b-87ed00f136cf","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Universal method for stochastic composite optimization problems , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:b4655fcbf09b921bc1ea8798bad9dc482867c0f1d1b6a3b00737c7acda1292c9","observation_id":"28efe6f4-0413-4955-9415-680bfb6c9f07","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.12591","last_updated":"2018-07-31T17:42:41Z","snapshot_observed_at":"2026-08-04T03:48:48.072279Z","submitted_at":"2018-05-31T17:56:28Z","title":"On Acceleration with Noise-Corrupted Gradients","version":3},"cited_work":{"arxiv_id":"1805.12591","doi":null,"metadata_source":"pith","pith_arxiv_id":"1805.12591","snapshot_observed_at":"2026-07-04T06:59:37.593176Z","title":"On Acceleration with Noise-Corrupted Gradients","venue":"math.OC","work_id":"82f836a4-a99e-412d-9df4-aad88dad68a5","year":2018},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"cited_paper":"/paper/1805.12591","citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:0d337e9f0130824cd23b78314b0cf438547d0219e7d16367e2a61d080f187b4f","observation_id":"c5e2c494-55d5-4c94-b34e-9df4c6b29c4b","resolution":{"observed_at":"2026-07-04T06:59:37.594547Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Strong and weak convexity of sets and functions , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:3620c45c2261bf701ec25212a1dbdbfd2cd917ea63545919500c51ab8aaf2eea","observation_id":"3745c0ee-4d0b-4bed-9c9d-71ecabf0c657","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"R-convexity of the integral of set-valued functions , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:cdfd8501e827fc059db4f2c8e458bebec08826ab8c5dd01b98006cc8ea75738f","observation_id":"a9eace6a-ef0b-4c9e-adeb-601a328b38d4","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Strongly convex analysis , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:3f792b207f90184a2830fe4d55819af7d6cf5babd458906985ced2cf369c39e6","observation_id":"86d07278-8caa-49c3-a70e-e381a440c782","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"On strongly convex sets and strongly convex functions , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:61f9431efc05dd8f06af1636b4aacc50aec341fd2ba471cdded57dd1789f56cd","observation_id":"87895d9e-44bf-409b-b12d-2136c1e9d3dc","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Exact post-selection inference, with application to the lasso , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:2b35933978fbfd55dd89c6228a648313a6eab7449ad48674329a8e9f1fdcaa01","observation_id":"f9d49830-e549-487a-96fc-8f21296464f3","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Valid post-selection inference , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:a16626bc6085c8d6e495e8ad4dea55b1be6c18032fc27d26931e626f4c323ccb","observation_id":"b6c38c0c-6f5d-4636-a3a4-334a427388c7","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Controlling the false discovery rate: a practical and powerful approach to multiple testing , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:35c3d4ce8c896186917e393036fcb84ff137e65647c03f679db76ecc4d841009","observation_id":"0f7601a8-6cc8-430b-9ba0-1383a4d11187","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Neighbourhood Retractions of Nonconvex Sets in a Hilbert Space via Sublinear Functionals , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:c041be834434cc79c5d6c83470e7511258aac0f027d1939cc05ab530e2cbe33f","observation_id":"f4f997e6-e0b4-49db-b8f0-56d9f58d2d35","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"On the vector sum of two convex sets in space , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:f7583a3b0531a4850b051edc76dfba58549cef1f119ee63b9b0868c8d53bccfb","observation_id":"71a15b21-266a-40d1-9720-cfd0404d1e55","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Strong and weak convexity of closed sets in a Hilbert space , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:f32c3c6f6ae9d99a26b015f1e613b70779843fcfc14aad900600c7813b06c5ac","observation_id":"bb839453-abf1-4da0-9d8f-e2d9436ffffb","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Smoothing and first order methods: A unified framework , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:ebd66e963e3b80798c5c8253c1c2333d3f2458db22fb80b6434675576a3d8ed4","observation_id":"0b7e7af6-fe7e-4c12-b7a9-c6fdba31ce2d","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Convex bodies: the Brunn--Minkowski theory , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:47622f7e83620735ba0a547d808271e08ebb5091e0694403af70ac56b2fe0b89","observation_id":"3a4bd80d-3ea6-4923-a22a-cfed2317de2b","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"First order methods beyond convexity and Lipschitz gradient continuity with applications to quadratic inverse problems , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:0c4b2cc2481188fb7ef1333094419a5b3bb7fc45448b1c37d68d43cefa8d586c","observation_id":"d7a86088-2595-413a-b060-e64dc846191f","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1901.10791","last_updated":"2021-02-17T18:40:41Z","snapshot_observed_at":"2026-07-06T07:30:00.126118Z","submitted_at":"2019-01-30T12:53:59Z","title":"Quartic First-Order Methods for Low-Rank Minimization","version":3},"cited_work":{"arxiv_id":"1901.10791","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1901.10791","snapshot_observed_at":"2026-07-04T06:59:37.551023Z","title":"arXiv preprint arXiv:1901.10791 , title =","venue":null,"work_id":"5c1dd38c-ff11-44ea-a2dc-8d155ba10d20","year":1901},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"cited_paper":"/paper/1901.10791","citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:2f30f4a34808f75e094423370c3535ca9d44debc2a76e42fc9fe25127e007d8a","observation_id":"33c840c3-5d84-4d6b-b6a5-de286e0df1c7","resolution":{"observed_at":"2026-07-04T06:59:37.552349Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"_0 penalized maximum likelihood for sparse directed acyclic graphs , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:a1da4179e10ece2a2243b429c43ec1e5b33f79d44e91c7ccd68be07eea6ba244","observation_id":"5ae1a081-07fb-4577-991c-eed89eb16309","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Learning directed acyclic graph models based on sparsest permutations , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:f1b47d22f577ecf2067989c8e277c0b5841ce1e305f0941101ea1cfa8d805a80","observation_id":"4f847157-5db6-4cae-8773-a4b6dc389585","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Some comments on Wolfe's ``away step'' , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":89,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:265040c0a24c7c02afa8f556082ddbc55fc8ad7b13b79eab4555576c358bfef6","observation_id":"de945af4-6b4a-4fff-a028-8b81059f213f","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Vanishing Price of Decentralization in Large Coordinative Nonconvex Optimization , volume =","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:7350991e132464f1a8873e13d88c7a17b39d723734eafef44a3751162198faca","observation_id":"bbf58cc9-7508-4e9b-91f9-7f5f2bf16559","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"A geometric framework for nonconvex optimization duality using augmented Lagrangian functions , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:62402e84a4c586a55719aa2eba918182ffb6edfd146b7817cd0b7e8e7218d1f1","observation_id":"4ec4452d-4c07-4e19-a80d-d9d3668e7761","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Updating the inverse of a matrix , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":92,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:668763941ac55a48b1bece189b982aa4b8daad89e50ce66ab6ccfc9bab3a0fdf","observation_id":"fe8ec714-9a1c-477b-8e49-6204a82abba5","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Panning for gold:`model-X'knockoffs for high dimensional controlled variable selection , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":93,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:e6e13e57fc5926596e33332403241971842270534a7e8b1de5ec558708aed2de","observation_id":"bd1ae17c-f17f-466f-b70b-c9dacfbd0ec9","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Controlling the false discovery rate via knockoffs , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":94,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:8eec146c8a3534adca6368bf78732301a83bec38ea2528da6a5cb704baa5be01","observation_id":"449d0a70-6556-4fa3-9d84-037d15b843e4","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"A knockoff filter for high-dimensional selective inference , volume =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:e9ffcfe04952390bcfafc6ef872bf52ca667e6c7622691abe0e37c17a9068959","observation_id":"72b53725-afab-4736-b572-362abae6792f","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.08590","last_updated":"2020-06-15T15:14:39Z","snapshot_observed_at":"2026-08-04T05:43:52.116953Z","submitted_at":"2019-10-18T19:05:00Z","title":"Anderson Acceleration of Proximal Gradient Methods","version":2},"cited_work":{"arxiv_id":"1910.08590","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1910.08590","snapshot_observed_at":"2026-07-04T06:59:37.612483Z","title":"arXiv preprint arXiv:1910.08590 , title =","venue":null,"work_id":"c1aca03e-e837-434d-a12d-be08a38dedeb","year":1910},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":96,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"cited_paper":"/paper/1910.08590","citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:466d29d208e25d3f02f532a4b4f7a58ad81b1a5c5d47bc4505a5257a6b4ce98d","observation_id":"a2c67d5d-03bb-4ac4-a37e-57174330e20d","resolution":{"observed_at":"2026-07-04T06:59:37.613846Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Trajectory of alternating direction method of multipliers and adaptive acceleration , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":97,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:2c69d309353ced8ea92dbb3a407d6dbdcfdad8868dd2122e479796e08e8fb8de","observation_id":"fb029c43-eff3-46b7-8392-9fa0b67153d7","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.11482","last_updated":"2020-11-17T00:28:23Z","snapshot_observed_at":"2026-07-06T08:17:50.342425Z","submitted_at":"2019-08-29T23:47:38Z","title":"Anderson Accelerated Douglas-Rachford Splitting","version":4},"cited_work":{"arxiv_id":"1908.11482","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1908.11482","snapshot_observed_at":"2026-07-04T06:59:37.600027Z","title":"arXiv preprint arXiv:1908.11482 , title =","venue":null,"work_id":"e935f44b-8859-46d3-baf7-7e1e3db931b5","year":1908},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":98,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"cited_paper":"/paper/1908.11482","citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:bf0d8b4e7875cf96befe6777186e241afea2fdf8a36861c83859bd967f2db3e9","observation_id":"abf276f5-b3b9-48e0-8d46-420e726825a6","resolution":{"observed_at":"2026-07-04T06:59:37.601404Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Nonlinear acceleration of stochastic algorithms , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":99,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:cb43e66d3b1abe5c07dd8d20a178965ccf28a9c5899cb445c8f74ff53319776e","observation_id":"d556c685-101f-4ce5-ba15-6925c238048a","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T14:00:19.385619Z","title":"Regularized nonlinear acceleration , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods","version":1},"reference_index":100,"source":"arxiv_source","source_observed_at":"2026-06-26T14:00:19.385619Z"},"links":{"citing_paper":"/paper/2606.21354"},"observation_digest":"sha256:5b967d9849672d514e27b2a90f672978dc9dc90c1a7d40b426fba44b1956ecd1","observation_id":"77440b42-64d1-4dfa-86b6-eef862f2fdf9","resolution":{"observed_at":"2026-06-26T14:00:19.385619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.21354","last_updated":"2026-06-19T11:54:49Z","latest_version":1,"primary_category":"math.OC","snapshot_observed_at":"2026-07-06T23:56:21.824303Z","submitted_at":"2026-06-19T11:54:49Z","title":"Restart and Adaptive Acceleration in Stochastic Gradient Methods"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":4,"parse_uncertain":0,"unresolved":84,"verified_exact":12,"verified_fuzzy":0},"total_outbound_references":300},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 100 of 300 outbound references and 0 inbound Pith citation observations for arXiv:2606.21354."}