{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QF5OMNBVKENFPHZYTOYTBNLNKG","short_pith_number":"pith:QF5OMNBV","schema_version":"1.0","canonical_sha256":"817ae63435511a579f389bb130b56d51b3b11b81312b2ca951132e0a8c98ab9a","source":{"kind":"arxiv","id":"2401.08024","version":1},"attestation_state":"computed","paper":{"title":"AdaBB: Adaptive Barzilai-Borwein Method for Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Danqing Zhou, Junfeng Yang, Shiqian Ma","submitted_at":"2024-01-16T00:42:34Z","abstract_excerpt":"In this paper, we propose AdaBB, an adaptive gradient method based on the Barzilai-Borwein stepsize. The algorithm is line-search-free and parameter-free, and essentially provides a convergent variant of the Barzilai-Borwein method for general unconstrained convex optimization. We analyze the ergodic convergence of the objective function value and the convergence of the iterates for solving general unconstrained convex optimization. Compared with existing works along this line of research, our algorithm gives the best lower bounds on the stepsize and the average of the stepsizes. Moreover, we "},"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":"2401.08024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-01-16T00:42:34Z","cross_cats_sorted":[],"title_canon_sha256":"c86c3706d11e24c8cab83e5953b3632ccd170dd6b38efa491ca9ee935ab447bd","abstract_canon_sha256":"9e1990d4fa795f8d485c993f8e216001739f9cdbc4c8ba65d528c3891d79666a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:06.149782Z","signature_b64":"tWrjOlZXM5UKSXSK/wZTn7Bf1QOnXednXSgExIafhXX2PpYnQ1Jt40roivqhbbrN2j7w8TVzGcdBe+RqC2TxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"817ae63435511a579f389bb130b56d51b3b11b81312b2ca951132e0a8c98ab9a","last_reissued_at":"2026-07-05T07:34:06.149433Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:06.149433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaBB: Adaptive Barzilai-Borwein Method for Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Danqing Zhou, Junfeng Yang, Shiqian Ma","submitted_at":"2024-01-16T00:42:34Z","abstract_excerpt":"In this paper, we propose AdaBB, an adaptive gradient method based on the Barzilai-Borwein stepsize. The algorithm is line-search-free and parameter-free, and essentially provides a convergent variant of the Barzilai-Borwein method for general unconstrained convex optimization. We analyze the ergodic convergence of the objective function value and the convergence of the iterates for solving general unconstrained convex optimization. Compared with existing works along this line of research, our algorithm gives the best lower bounds on the stepsize and the average of the stepsizes. Moreover, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08024","kind":"arxiv","version":1},"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/2401.08024/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":"2401.08024","created_at":"2026-07-05T07:34:06.149484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08024v1","created_at":"2026-07-05T07:34:06.149484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08024","created_at":"2026-07-05T07:34:06.149484+00:00"},{"alias_kind":"pith_short_12","alias_value":"QF5OMNBVKENF","created_at":"2026-07-05T07:34:06.149484+00:00"},{"alias_kind":"pith_short_16","alias_value":"QF5OMNBVKENFPHZY","created_at":"2026-07-05T07:34:06.149484+00:00"},{"alias_kind":"pith_short_8","alias_value":"QF5OMNBV","created_at":"2026-07-05T07:34:06.149484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08783","citing_title":"OptMuon: Closed-Loop Orthogonalized Momentum Methods for Stochastic Optimization with Zero-Noise Optimality","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08783","citing_title":"OptMuon: Closed-Loop Orthogonalized Momentum Methods for Stochastic Optimization with Zero-Noise Optimality","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14291","citing_title":"Projected gradient methods for nonconvex and stochastic smooth optimization: new complexities and auto-conditioned stepsizes","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11043","citing_title":"A Proximal Stochastic Gradient Method with Adaptive Step Size and Variance Reduction for Convex Composite Optimization","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QF5OMNBVKENFPHZYTOYTBNLNKG","json":"https://pith.science/pith/QF5OMNBVKENFPHZYTOYTBNLNKG.json","graph_json":"https://pith.science/api/pith-number/QF5OMNBVKENFPHZYTOYTBNLNKG/graph.json","events_json":"https://pith.science/api/pith-number/QF5OMNBVKENFPHZYTOYTBNLNKG/events.json","paper":"https://pith.science/paper/QF5OMNBV"},"agent_actions":{"view_html":"https://pith.science/pith/QF5OMNBVKENFPHZYTOYTBNLNKG","download_json":"https://pith.science/pith/QF5OMNBVKENFPHZYTOYTBNLNKG.json","view_paper":"https://pith.science/paper/QF5OMNBV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08024&json=true","fetch_graph":"https://pith.science/api/pith-number/QF5OMNBVKENFPHZYTOYTBNLNKG/graph.json","fetch_events":"https://pith.science/api/pith-number/QF5OMNBVKENFPHZYTOYTBNLNKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QF5OMNBVKENFPHZYTOYTBNLNKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QF5OMNBVKENFPHZYTOYTBNLNKG/action/storage_attestation","attest_author":"https://pith.science/pith/QF5OMNBVKENFPHZYTOYTBNLNKG/action/author_attestation","sign_citation":"https://pith.science/pith/QF5OMNBVKENFPHZYTOYTBNLNKG/action/citation_signature","submit_replication":"https://pith.science/pith/QF5OMNBVKENFPHZYTOYTBNLNKG/action/replication_record"}},"created_at":"2026-07-05T07:34:06.149484+00:00","updated_at":"2026-07-05T07:34:06.149484+00:00"}