{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F35EYBTAGTO5YACNAPZ5X5CCV6","short_pith_number":"pith:F35EYBTA","schema_version":"1.0","canonical_sha256":"2efa4c066034dddc004d03f3dbf442afaecb0b11794087acf8996eae2dfe67dc","source":{"kind":"arxiv","id":"2412.14291","version":2},"attestation_state":"computed","paper":{"title":"Projected gradient methods for nonconvex and stochastic smooth optimization: new complexities and auto-conditioned stepsizes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Guanghui Lan, Tianjiao Li, Yangyang Xu","submitted_at":"2024-12-18T19:34:16Z","abstract_excerpt":"We present a novel class of projected gradient (PG) methods for minimizing a smooth but not necessarily convex function over a convex compact set. We first provide a novel analysis of the constant-stepsize PG method, achieving the best-known iteration complexity for finding an approximate stationary point of the problem. We then develop an \"auto-conditioned\" projected gradient (AC-PG) variant that achieves the same iteration complexity without requiring the input of the Lipschitz constant of the gradient or any line search procedure. The key idea is to estimate the Lipschitz constant using fir"},"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":"2412.14291","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-12-18T19:34:16Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"460551bd77cb7be43036c8fe656aef1354b3ee7008a4679ddf15d42cff49b005","abstract_canon_sha256":"c9bc2b74696358f5e5293b3a7ea218515171d00fcb1bb87a4b7d1e2baa2b471f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:01.626554Z","signature_b64":"grrX5cAhuB2U81zQEE9rjSBJJQPoD/IJ/09AKKpCy0OLlQ5znX20YlYLV904OE+1SL+DRbZgNOTAhXtSuOo9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2efa4c066034dddc004d03f3dbf442afaecb0b11794087acf8996eae2dfe67dc","last_reissued_at":"2026-05-17T23:39:01.625864Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:01.625864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Projected gradient methods for nonconvex and stochastic smooth optimization: new complexities and auto-conditioned stepsizes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Guanghui Lan, Tianjiao Li, Yangyang Xu","submitted_at":"2024-12-18T19:34:16Z","abstract_excerpt":"We present a novel class of projected gradient (PG) methods for minimizing a smooth but not necessarily convex function over a convex compact set. We first provide a novel analysis of the constant-stepsize PG method, achieving the best-known iteration complexity for finding an approximate stationary point of the problem. We then develop an \"auto-conditioned\" projected gradient (AC-PG) variant that achieves the same iteration complexity without requiring the input of the Lipschitz constant of the gradient or any line search procedure. The key idea is to estimate the Lipschitz constant using fir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14291","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2412.14291","created_at":"2026-05-17T23:39:01.625969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14291v2","created_at":"2026-05-17T23:39:01.625969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14291","created_at":"2026-05-17T23:39:01.625969+00:00"},{"alias_kind":"pith_short_12","alias_value":"F35EYBTAGTO5","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"F35EYBTAGTO5YACN","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"F35EYBTA","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2603.23492","citing_title":"Universal and Parameter-free Gradient Sliding for Composite Optimization","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15512","citing_title":"Auto-Conditioned Frank-Wolfe Algorithms","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02763","citing_title":"Adaptive Newton-CG methods with global and local analysis for unconstrained optimization with H\\\"older continuous Hessian","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06525","citing_title":"Stochastic Auto-conditioned Fast Gradient Methods with Optimal Rates","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F35EYBTAGTO5YACNAPZ5X5CCV6","json":"https://pith.science/pith/F35EYBTAGTO5YACNAPZ5X5CCV6.json","graph_json":"https://pith.science/api/pith-number/F35EYBTAGTO5YACNAPZ5X5CCV6/graph.json","events_json":"https://pith.science/api/pith-number/F35EYBTAGTO5YACNAPZ5X5CCV6/events.json","paper":"https://pith.science/paper/F35EYBTA"},"agent_actions":{"view_html":"https://pith.science/pith/F35EYBTAGTO5YACNAPZ5X5CCV6","download_json":"https://pith.science/pith/F35EYBTAGTO5YACNAPZ5X5CCV6.json","view_paper":"https://pith.science/paper/F35EYBTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14291&json=true","fetch_graph":"https://pith.science/api/pith-number/F35EYBTAGTO5YACNAPZ5X5CCV6/graph.json","fetch_events":"https://pith.science/api/pith-number/F35EYBTAGTO5YACNAPZ5X5CCV6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F35EYBTAGTO5YACNAPZ5X5CCV6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F35EYBTAGTO5YACNAPZ5X5CCV6/action/storage_attestation","attest_author":"https://pith.science/pith/F35EYBTAGTO5YACNAPZ5X5CCV6/action/author_attestation","sign_citation":"https://pith.science/pith/F35EYBTAGTO5YACNAPZ5X5CCV6/action/citation_signature","submit_replication":"https://pith.science/pith/F35EYBTAGTO5YACNAPZ5X5CCV6/action/replication_record"}},"created_at":"2026-05-17T23:39:01.625969+00:00","updated_at":"2026-05-17T23:39:01.625969+00:00"}