{"as_of":"2026-08-07T07:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:eb38b27e4752cc917e19c62e72168944c7ed358743d7085a03f8d56bc270955d","coverage":[{"denominator":33,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":33,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-25T09:52:34.427619Z","state":"measured"},{"denominator":33,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":33,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/1907.01849/citation-record","integrity":"/paper/1907.01849/integrity","json":"/paper/1907.01849/citation-record.json","paper":"/paper/1907.01849"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Diffusion learning in non-con vex envi- ronments","venue":null,"work_id":"28a8735a-74e4-44f4-bf36-18e8bc5ee625","year":2019},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:125f0dd81b8c5c9e124d7f13af8178da95a90512b649fe328ac269b163be7be6","observation_id":"b48a4f93-a4e2-4912-b7b8-fb1bd251e2f9","resolution":{"observed_at":"2026-05-25T09:55:37.543925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Distributed learning in non-c onvex environments – Part I: Agreement at a Linear rate","venue":null,"work_id":"00a02a39-3d55-444e-9c9c-0ecf17c3655e","year":2019},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:e2cc51218ff1241a38952ec71c9ef40ffd052af1c1f4eb71d713db2fa45b7fcf","observation_id":"7fc2d9e7-7602-4768-be60-930e2a0058d2","resolution":{"observed_at":"2026-05-25T09:55:37.540341Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Distributed subgradient meth ods for multi- agent optimization","venue":null,"work_id":"b2d2677b-c8ae-4a72-8014-bd60389d466d","year":2009},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:95488ece57c1d8c8f5dc2a332b17ef094731e281f1ff49f6f4832198e1b7630b","observation_id":"68478ee1-8b2e-4a67-b114-1feb0434a667","resolution":{"observed_at":"2026-05-25T09:55:37.537204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Adaptation, learning, and optimization ov er networks","venue":null,"work_id":"9b740fc2-8b27-4614-878a-89c758acf13f","year":2014},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:457082e83816d42b30b9c68e42a0e7fcaf5f181b74be2a64d3a59ad78f53d86c","observation_id":"316e4a13-7b8f-472a-9b13-23917e042de6","resolution":{"observed_at":"2026-05-25T09:55:37.472180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"On the learning behavior of adapt ive networks - Part I: Transient analysis","venue":null,"work_id":"52a2f33d-108a-492c-b15d-de009070f947","year":2015},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:e9b72394538d4b2d74cc94c41666660648b1847a3de30abac3423883062c8c2b","observation_id":"054fd8ab-ad45-4fb5-8b0a-fa3d2a1aca05","resolution":{"observed_at":"2026-05-25T09:55:37.508303Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.07266","last_updated":"2019-04-09T22:23:17Z","snapshot_observed_at":"2026-07-06T07:39:53.237226Z","submitted_at":"2019-03-18T06:29:08Z","title":"Distributed stochastic optimization with gradient tracking over strongly-connected networks","version":2},"cited_work":{"arxiv_id":"1903.07266","doi":null,"metadata_source":"pith","pith_arxiv_id":"1903.07266","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Distributed stochastic optimization with gradient tracking over strongly-connected networks","venue":"cs.LG","work_id":"5ab96d20-3914-4237-891d-b94e4b6555c5","year":2019},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"cited_paper":"/paper/1903.07266","citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:6563f205f9d02aa08c925347b9642ca31de2b51a8fef2cab1a2d431e263d100d","observation_id":"aeb10823-31d9-4e33-8477-82bee007b204","resolution":{"observed_at":"2026-05-25T09:55:36.547979Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Stochastic g radient descent with finite samples sizes","venue":null,"work_id":"9796391a-ae3e-4390-a52c-1ecab2903c94","year":2016},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:4f2994597667a17eb58a0e9fbc8473665c1895aa7b58f3a152fe1999f90ff53d","observation_id":"5038ee11-3696-4bfa-bcd0-0877d6ea455a","resolution":{"observed_at":"2026-05-25T09:55:37.530406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Extra: An exact first-or der algorithm for decentralized consensus optimization","venue":null,"work_id":"b7d6c3b9-daa9-4477-ac44-aa3be087309a","year":2015},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:19ea74144928e42e272a14567c1a27d5e98c592d1832ee3afb0d84e3c57786b9","observation_id":"cd48a971-c22b-4a01-913e-c7c5ea25dcfc","resolution":{"observed_at":"2026-05-25T09:55:37.520387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Exact diffusio n for distributed optimization and learning – Part II: Convergen ce analysis","venue":null,"work_id":"fb327e1f-cacd-42a6-b4dc-64d50b37ca22","year":2019},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:9b72b7511eb8de62b6fcb8c2cf92c1c297714733271defdb8fb23828753185ac","observation_id":"d62ab078-21fe-4c62-ba04-64adede71c61","resolution":{"observed_at":"2026-05-25T09:55:37.486612Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Diffusion strategies o utperform consensus strategies for distributed estimation over adap tive networks","venue":null,"work_id":"b90d7842-11c9-4780-b3fa-3c144c3c90bf","year":2012},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:3fa4365cbcacf9c1d5bcd7f64ec79633bb0e63e13e54b2d71fedf555cc022cce","observation_id":"0c20271b-39be-49a4-803a-73a16291bb4d","resolution":{"observed_at":"2026-05-25T09:55:37.461398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"On the learning behavior of adap tive networks – Part II: Performance analysis","venue":null,"work_id":"5df5c88f-cfca-4f37-bcfc-ca717b90975e","year":2015},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:c17b46c183f1389af705ec28e4f56bffc07f27518eaddbfe55bc3f4e852ca977","observation_id":"2843d5d0-896f-4f3a-986e-abe818053e56","resolution":{"observed_at":"2026-05-25T09:55:37.465038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Prox imal multitask learning over networks with sparsity-inducing coregulari zation","venue":null,"work_id":"96754a0d-5800-48bc-aa33-4217626d8c80","year":2016},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:c75737f6858594c1c4b37c60132ac0f7a9665fdf259d1b161ee74f9cc5201d0e","observation_id":"4c998181-afde-417e-991a-f912615cf525","resolution":{"observed_at":"2026-05-25T09:55:37.454374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Adaptive penalty-based dis tributed stochastic convex optimization","venue":null,"work_id":"21ac96a0-7611-41ca-9e89-55e9a0a17a71","year":2014},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:fadcbe2e3544e096e915b2ee986b7a1de8b33aae0ef36bf86b150d8d4dfb5b04","observation_id":"4f6b0855-766b-41c5-b91b-4b7edc9250a9","resolution":{"observed_at":"2026-05-25T09:55:37.493268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Performance limits of stochast ic sub-gradient learning, Part II: Multi-agent case","venue":null,"work_id":"a3687857-4271-46ed-baed-d4024026c557","year":2018},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:5067a8b992bae542b5439ca9c18514c284ad70cabe34f5c541762447d62717d3","observation_id":"57215295-3b71-4dbc-b592-da9dd75e1233","resolution":{"observed_at":"2026-05-25T09:55:37.523847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cubic regularization of n ewton method and its global performance","venue":null,"work_id":"24531d02-8886-4436-8371-a2c1b1101915","year":2006},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:c5d53f44162a1833523f7ea4bc6a1520ce67696c532fd46ec7dadc848340a726","observation_id":"742f2b60-05b7-45ec-944d-3342a1fda7df","resolution":{"observed_at":"2026-05-25T09:55:37.500221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"SPIDER: Near-opt imal non- convex optimization via stochastic path-integrated differential estimator","venue":null,"work_id":"aa2e34ce-1544-4ffc-b6c6-7218dfe78569","year":2018},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:9665c85e8afff51bffa06b6dc51bcbe90f05dcd8cf80fd342e356c5b15fa24a2","observation_id":"82766bba-8757-48a2-8f79-116451616ada","resolution":{"observed_at":"2026-05-25T09:55:37.458020Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"NEON2: Finding local minima via first-order oracles","venue":null,"work_id":"fd19bc36-df99-4395-ae7f-da40efdbf19f","year":2018},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:8c9992ac67dc97a4082c026fa3f5e3f2e4c4ba9407841f4676ef309d0807e0f4","observation_id":"06f3657f-478e-49c5-b592-f0610d175db7","resolution":{"observed_at":"2026-05-25T09:55:37.514731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Natasha 2: Faster non-convex optimizat ion than SGD","venue":null,"work_id":"1798069f-bb22-4df6-a4bc-4688548503c9","year":2018},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:1767ce7af48d8955f758508572dab65e17748121a68b40be2fed768ac5957428","observation_id":"ab8b234e-b097-4e46-b094-f2a82f731aa1","resolution":{"observed_at":"2026-05-25T09:55:37.504800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Gra dient descent only converges to minimizers","venue":null,"work_id":"6128519b-d94a-4a84-9bb1-776334ba09f3","year":2016},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:8559b9364461cfd52f44d64ab15203fb393e804fc0238b0fdbf797534d00adac","observation_id":"4c0eaf1c-3d5b-4977-88c4-c35b5373320a","resolution":{"observed_at":"2026-05-25T09:55:37.468777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1809.08694","last_updated":"2020-05-25T16:53:35Z","snapshot_observed_at":"2026-08-03T01:11:43.850652Z","submitted_at":"2018-09-23T23:06:39Z","title":"Second-order Guarantees of Distributed Gradient Algorithms","version":5},"cited_work":{"arxiv_id":"1809.08694","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1809.08694","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Second-o rder guaran- tees of distributed gradient algorithms","venue":null,"work_id":"baa8e934-c45a-4ae7-9f30-a83bb8bf64ee","year":2018},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"cited_paper":"/paper/1809.08694","citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:99a439fd5bfa6eb52a296964540f7af76a2d9cabd56c08174358ee14f736bf00","observation_id":"6c34fe7f-4161-41e9-b56a-68284cebf116","resolution":{"observed_at":"2026-05-25T09:55:36.564336Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Recursive stochastic algori thms for global optimization in Rd","venue":null,"work_id":"006817c7-cd7f-4a9e-8030-cc009acf307b","year":1991},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:6a59e02ac5ac8e1931585c2d256a1fefeb5cbd201f9e850f207b74a6277f3524","observation_id":"4f9e72c3-b0d9-4275-8902-525fe888f135","resolution":{"observed_at":"2026-05-25T09:55:37.527046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.07258","last_updated":"2019-03-18T05:16:37Z","snapshot_observed_at":"2026-07-06T07:39:53.237226Z","submitted_at":"2019-03-18T05:16:37Z","title":"Annealing for Distributed Global Optimization","version":1},"cited_work":{"arxiv_id":"1903.07258","doi":null,"metadata_source":"pith","pith_arxiv_id":"1903.07258","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Annealing for Distributed Global Optimization","venue":"math.OC","work_id":"ccfef1a1-5c60-445d-8a35-1dad780c9a97","year":2019},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"cited_paper":"/paper/1903.07258","citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:60eeb67330a4b194809983198bca69a547301eaf18fb98cb68febd5d0fde0f15","observation_id":"fa750ff3-8adb-4157-901d-060a54b32945","resolution":{"observed_at":"2026-05-25T09:55:36.568723Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1705.10412","last_updated":"2017-11-05T16:35:27Z","snapshot_observed_at":"2026-08-04T05:13:59.649085Z","submitted_at":"2017-05-29T23:03:01Z","title":"Gradient Descent Can Take Exponential Time to Escape Saddle Points","version":2},"cited_work":{"arxiv_id":"1705.10412","doi":null,"metadata_source":"pith","pith_arxiv_id":"1705.10412","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Gradient Descent Can Take Exponential Time to Escape Saddle Points","venue":"math.OC","work_id":"8752ef65-4e49-451e-8c11-3eac2f7bc292","year":2017},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"cited_paper":"/paper/1705.10412","citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:7f54445cbb1b02abb84c23dc7f78907ba99c4b1151c9b60391c428fb2e977c91","observation_id":"ae68b1fe-c06e-4521-938c-ce79b762be27","resolution":{"observed_at":"2026-05-25T09:55:36.580148Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Escaping from saddl e pointsonline stochastic gradient for tensor decompositio n","venue":null,"work_id":"ff702d55-fe63-4131-9869-b4e1863d7b3d","year":2015},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:3c6f3fe5439964b4d314556d8626008630234234d5ae8d882179970808406241","observation_id":"9c6d6388-d678-4a14-a063-4253aeb467ca","resolution":{"observed_at":"2026-05-25T09:55:37.475791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"How to escape saddle points efficiently","venue":null,"work_id":"eaa27663-27cb-4875-99ed-7a1d2df9103c","year":2017},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:bfbf416c4421dd5295df8375f6cf283a27282b244ef23042eab71f9a24768f10","observation_id":"805ccb71-6ad2-4016-b956-177d2e925d90","resolution":{"observed_at":"2026-05-25T09:55:37.533920Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.04811","last_updated":"2019-09-04T03:26:59Z","snapshot_observed_at":"2026-07-06T07:32:49.581638Z","submitted_at":"2019-02-13T09:44:02Z","title":"On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points","version":2},"cited_work":{"arxiv_id":"1902.04811","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1902.04811","snapshot_observed_at":"2026-07-02T07:36:45.174590Z","title":"Stochas- tic gradient descent escapes saddle points efficiently","venue":null,"work_id":"7d604b92-f948-4aa5-b5c4-d99955d9da7f","year":2019},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"cited_paper":"/paper/1902.04811","citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:d4fc973fd44cd5db52a74be7d6ec8fe543a33f1564b4fcc0a6eb1f61ca8a0f5d","observation_id":"2f123d49-9a9a-4cf4-9cc6-d8625eafd6d8","resolution":{"observed_at":"2026-05-25T09:55:36.558456Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05999","last_updated":"2018-09-16T16:18:17Z","snapshot_observed_at":"2026-07-06T06:28:33.221907Z","submitted_at":"2018-03-15T20:48:06Z","title":"Escaping Saddles with Stochastic Gradients","version":2},"cited_work":{"arxiv_id":"1803.05999","doi":null,"metadata_source":"pith","pith_arxiv_id":"1803.05999","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Escaping Saddles with Stochastic Gradients","venue":"cs.LG","work_id":"c7c4f3f3-c67a-48c7-8c60-e950b3e0ff9e","year":2018},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"cited_paper":"/paper/1803.05999","citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:581a52194cd72bdac5bef68918c8f73074b0e16ad1596fff64d449cce9597c3b","observation_id":"85764c71-8e8a-4851-a604-b71696123d09","resolution":{"observed_at":"2026-05-25T09:55:36.553099Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.00247","last_updated":"2019-06-04T12:23:24Z","snapshot_observed_at":"2026-07-06T07:30:28.869358Z","submitted_at":"2019-02-01T09:35:27Z","title":"Sharp Analysis for Nonconvex SGD Escaping from Saddle Points","version":2},"cited_work":{"arxiv_id":"1902.00247","doi":null,"metadata_source":"pith","pith_arxiv_id":"1902.00247","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Sharp Analysis for Nonconvex SGD Escaping from Saddle Points","venue":"math.OC","work_id":"ddf79e54-160f-4dac-9125-1308c80416d3","year":2019},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"cited_paper":"/paper/1902.00247","citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:f919f1730b87c123bb84c3ad82e1a84d5b13d0265f0dcf912b38fe52d816bf3b","observation_id":"041a77e5-032c-4dc6-9e2a-596207357959","resolution":{"observed_at":"2026-05-25T09:55:36.574587Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"NEXT: in-network nonconv ex optimiza- tion","venue":null,"work_id":"10847c34-db70-46cb-8f51-553bfb97b145","year":2016},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:029a4028403db9f8fe2e041bee2578db438d6b57c945963c807a4567ec1a882e","observation_id":"66924e47-7c68-4a7c-b9f1-c7826423c92e","resolution":{"observed_at":"2026-05-25T09:55:37.489878Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Global convergence of ADMM in nonconvex nonsmooth optimization","venue":null,"work_id":"6ca0d7d9-751e-4d11-8e50-2eeb358305b6","year":2019},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:c617294fdfc6c824b9f8f6d78624aca9bd53288383b81a3912e3c7ee107d47cf","observation_id":"83cdc552-a956-4c58-b943-f6fb0acbaf41","resolution":{"observed_at":"2026-05-25T09:55:37.479621Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Non-convex distributed opt imization","venue":null,"work_id":"97dd8c66-0e91-4909-b0d4-04ddbc341996","year":2017},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:4235ddd6686ade9b3daac057d71ec4284d51bc4c45b0fede7297ac3841c79b9f","observation_id":"a44234ce-d806-47a3-adb5-4a453aeea293","resolution":{"observed_at":"2026-05-25T09:55:37.496742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"5395d9b6-fa10-4f66-899b-90f12e7a9705","year":2003},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:ae8fd217dd9b2cdd0a409a26789dbe082afe4b38d5b963cec82f98973dd7087a","observation_id":"603a6f8b-5639-4766-8293-d92d94968cd8","resolution":{"observed_at":"2026-05-25T09:55:37.511460Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The Perron-Frobenius theorem: Some of its applications","venue":null,"work_id":"ba3730ab-072c-498d-bfe5-b7a8b6c974ad","year":2005},"citing_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-25T09:52:34.427619Z"},"links":{"citing_paper":"/paper/1907.01849"},"observation_digest":"sha256:f443625cf6dd53c102771aad23e10c1fea70d96efc649b0aa183a3fe6d16b8cb","observation_id":"9389384a-aef7-419d-ab52-31f969588a3b","resolution":{"observed_at":"2026-05-25T09:55:37.483136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","latest_version":1,"primary_category":"cs.MA","snapshot_observed_at":"2026-07-06T08:04:50.941443Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points"},"reference_resolution":{"displayed":33,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":1,"verified_exact":7,"verified_fuzzy":25},"total_outbound_references":33},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:1907.01849."}