{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5WVYQET3RGZPEVY5XJTCMJYQT5","short_pith_number":"pith:5WVYQET3","schema_version":"1.0","canonical_sha256":"edab88127b89b2f2571dba662627109f4601e8d24a9546d23b6d3750cd04bd50","source":{"kind":"arxiv","id":"2301.04431","version":4},"attestation_state":"computed","paper":{"title":"Adaptive proximal algorithms for convex optimization under local Lipschitz continuity of the gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Andreas Themelis, Lorenzo Stella, Panagiotis Patrinos, Puya Latafat","submitted_at":"2023-01-11T12:19:28Z","abstract_excerpt":"Backtracking linesearch is the de facto approach for minimizing continuously differentiable functions with locally Lipschitz gradient. In recent years, it has been shown that in the convex setting it is possible to avoid linesearch altogether, and to allow the stepsize to adapt based on a local smoothness estimate without any backtracks or evaluations of the function value. In this work we propose an adaptive proximal gradient method, adaPG, that uses novel estimates of the local smoothness modulus which leads to less conservative stepsize updates and that can additionally cope with nonsmooth "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2301.04431","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-01-11T12:19:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"177e3117d425ad1d9ffea4175fb6d4aa390d06f5960e5a972363c4989f539ab4","abstract_canon_sha256":"5478f94a29538c5c7a03bc2bd8a404062353e7e2a8e4b6b36b55546bb438136a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:19.618202Z","signature_b64":"3kZ65TVaMHnOl+w0qVg/h6LiDtGF082/r7OcuMpsF7sIX5kCAhQzw38dndqmOQOUp4GFOA7Vl4MvJNCiVHH5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edab88127b89b2f2571dba662627109f4601e8d24a9546d23b6d3750cd04bd50","last_reissued_at":"2026-07-05T07:55:19.617696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:19.617696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive proximal algorithms for convex optimization under local Lipschitz continuity of the gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Andreas Themelis, Lorenzo Stella, Panagiotis Patrinos, Puya Latafat","submitted_at":"2023-01-11T12:19:28Z","abstract_excerpt":"Backtracking linesearch is the de facto approach for minimizing continuously differentiable functions with locally Lipschitz gradient. In recent years, it has been shown that in the convex setting it is possible to avoid linesearch altogether, and to allow the stepsize to adapt based on a local smoothness estimate without any backtracks or evaluations of the function value. In this work we propose an adaptive proximal gradient method, adaPG, that uses novel estimates of the local smoothness modulus which leads to less conservative stepsize updates and that can additionally cope with nonsmooth "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04431","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2301.04431/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2301.04431","created_at":"2026-07-05T07:55:19.617758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.04431v4","created_at":"2026-07-05T07:55:19.617758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04431","created_at":"2026-07-05T07:55:19.617758+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WVYQET3RGZP","created_at":"2026-07-05T07:55:19.617758+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WVYQET3RGZPEVY5","created_at":"2026-07-05T07:55:19.617758+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WVYQET3","created_at":"2026-07-05T07:55:19.617758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08174","citing_title":"Two Adaptive Accelerated Golden Ratio Primal--Dual Algorithms With an Application to Poisson Imaging Problem","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2412.14291","citing_title":"Projected gradient methods for nonconvex and stochastic smooth optimization: new complexities and auto-conditioned stepsizes","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WVYQET3RGZPEVY5XJTCMJYQT5","json":"https://pith.science/pith/5WVYQET3RGZPEVY5XJTCMJYQT5.json","graph_json":"https://pith.science/api/pith-number/5WVYQET3RGZPEVY5XJTCMJYQT5/graph.json","events_json":"https://pith.science/api/pith-number/5WVYQET3RGZPEVY5XJTCMJYQT5/events.json","paper":"https://pith.science/paper/5WVYQET3"},"agent_actions":{"view_html":"https://pith.science/pith/5WVYQET3RGZPEVY5XJTCMJYQT5","download_json":"https://pith.science/pith/5WVYQET3RGZPEVY5XJTCMJYQT5.json","view_paper":"https://pith.science/paper/5WVYQET3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.04431&json=true","fetch_graph":"https://pith.science/api/pith-number/5WVYQET3RGZPEVY5XJTCMJYQT5/graph.json","fetch_events":"https://pith.science/api/pith-number/5WVYQET3RGZPEVY5XJTCMJYQT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WVYQET3RGZPEVY5XJTCMJYQT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WVYQET3RGZPEVY5XJTCMJYQT5/action/storage_attestation","attest_author":"https://pith.science/pith/5WVYQET3RGZPEVY5XJTCMJYQT5/action/author_attestation","sign_citation":"https://pith.science/pith/5WVYQET3RGZPEVY5XJTCMJYQT5/action/citation_signature","submit_replication":"https://pith.science/pith/5WVYQET3RGZPEVY5XJTCMJYQT5/action/replication_record"}},"created_at":"2026-07-05T07:55:19.617758+00:00","updated_at":"2026-07-05T07:55:19.617758+00:00"}