{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:Y5ZCMVY6F7CYSWT23UZGRKOIZC","short_pith_number":"pith:Y5ZCMVY6","schema_version":"1.0","canonical_sha256":"c77226571e2fc5895a7add3268a9c8c8b683104f4fc0bdbf25a3b8baf728ed23","source":{"kind":"arxiv","id":"1607.01027","version":5},"attestation_state":"computed","paper":{"title":"Accelerate Stochastic Subgradient Method by Leveraging Local Growth Condition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","stat.ML"],"primary_cat":"math.OC","authors_text":"Qihang Lin, Tianbao Yang, Yi Xu","submitted_at":"2016-07-04T20:01:17Z","abstract_excerpt":"In this paper, a new theory is developed for first-order stochastic convex optimization, showing that the global convergence rate is sufficiently quantified by a local growth rate of the objective function in a neighborhood of the optimal solutions. In particular, if the objective function $F(\\mathbf w)$ in the $\\epsilon$-sublevel set grows as fast as $\\|\\mathbf w - \\mathbf w_*\\|_2^{1/\\theta}$, where $\\mathbf w_*$ represents the closest optimal solution to $\\mathbf w$ and $\\theta\\in(0,1]$ quantifies the local growth rate, the iteration complexity of first-order stochastic optimization for achi"},"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":"1607.01027","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-07-04T20:01:17Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA","stat.ML"],"title_canon_sha256":"d96c18e771a9a51c25395034b3ad162ae4a85682f0fa25055b7e52a698ba57d0","abstract_canon_sha256":"69b75d0428a4302aab498a535730124f7fb28982599991c413b22347c653933e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T18:09:52.048415Z","signature_b64":"FyLdbJioz7VdM/v+/jeHSOTRvf6Hk6Y/rKV3qSxraIglXpG9b7ZOVyPHk+4uO8jD+RSkoZIUr4N91NdRlGDHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c77226571e2fc5895a7add3268a9c8c8b683104f4fc0bdbf25a3b8baf728ed23","last_reissued_at":"2026-06-04T18:09:52.047947Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T18:09:52.047947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerate Stochastic Subgradient Method by Leveraging Local Growth Condition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","stat.ML"],"primary_cat":"math.OC","authors_text":"Qihang Lin, Tianbao Yang, Yi Xu","submitted_at":"2016-07-04T20:01:17Z","abstract_excerpt":"In this paper, a new theory is developed for first-order stochastic convex optimization, showing that the global convergence rate is sufficiently quantified by a local growth rate of the objective function in a neighborhood of the optimal solutions. In particular, if the objective function $F(\\mathbf w)$ in the $\\epsilon$-sublevel set grows as fast as $\\|\\mathbf w - \\mathbf w_*\\|_2^{1/\\theta}$, where $\\mathbf w_*$ represents the closest optimal solution to $\\mathbf w$ and $\\theta\\in(0,1]$ quantifies the local growth rate, the iteration complexity of first-order stochastic optimization for achi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.01027","kind":"arxiv","version":5},"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/1607.01027/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":"1607.01027","created_at":"2026-06-04T18:09:52.047998+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.01027v5","created_at":"2026-06-04T18:09:52.047998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.01027","created_at":"2026-06-04T18:09:52.047998+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5ZCMVY6F7CY","created_at":"2026-06-04T18:09:52.047998+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5ZCMVY6F7CYSWT2","created_at":"2026-06-04T18:09:52.047998+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5ZCMVY6","created_at":"2026-06-04T18:09:52.047998+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.09547","citing_title":"Stochastic algorithms with geometric step decay converge linearly on sharp functions","ref_index":66,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y5ZCMVY6F7CYSWT23UZGRKOIZC","json":"https://pith.science/pith/Y5ZCMVY6F7CYSWT23UZGRKOIZC.json","graph_json":"https://pith.science/api/pith-number/Y5ZCMVY6F7CYSWT23UZGRKOIZC/graph.json","events_json":"https://pith.science/api/pith-number/Y5ZCMVY6F7CYSWT23UZGRKOIZC/events.json","paper":"https://pith.science/paper/Y5ZCMVY6"},"agent_actions":{"view_html":"https://pith.science/pith/Y5ZCMVY6F7CYSWT23UZGRKOIZC","download_json":"https://pith.science/pith/Y5ZCMVY6F7CYSWT23UZGRKOIZC.json","view_paper":"https://pith.science/paper/Y5ZCMVY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.01027&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5ZCMVY6F7CYSWT23UZGRKOIZC/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5ZCMVY6F7CYSWT23UZGRKOIZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5ZCMVY6F7CYSWT23UZGRKOIZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5ZCMVY6F7CYSWT23UZGRKOIZC/action/storage_attestation","attest_author":"https://pith.science/pith/Y5ZCMVY6F7CYSWT23UZGRKOIZC/action/author_attestation","sign_citation":"https://pith.science/pith/Y5ZCMVY6F7CYSWT23UZGRKOIZC/action/citation_signature","submit_replication":"https://pith.science/pith/Y5ZCMVY6F7CYSWT23UZGRKOIZC/action/replication_record"}},"created_at":"2026-06-04T18:09:52.047998+00:00","updated_at":"2026-06-04T18:09:52.047998+00:00"}