{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2K6OGPYYXNSTHNDTYJ446AANJB","short_pith_number":"pith:2K6OGPYY","schema_version":"1.0","canonical_sha256":"d2bce33f18bb6533b473c279cf000d486ef95901a657871d02118bcde016194f","source":{"kind":"arxiv","id":"2312.02828","version":4},"attestation_state":"computed","paper":{"title":"Convergence Rates for Stochastic Approximation: Biased Noise with Unbounded Variance, and Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.OC","math.PR"],"primary_cat":"stat.ML","authors_text":"M. Vidyasagar, Rajeeva L. Karandikar","submitted_at":"2023-12-05T15:22:39Z","abstract_excerpt":"In this paper, we study the convergence properties of the Stochastic Gradient Descent (SGD) method for finding a stationary point of a given objective function $J(\\cdot)$. The objective function is not required to be convex. Rather, our results apply to a class of ``invex'' functions, which have the property that every stationary point is also a global minimizer. First, it is assumed that $J(\\cdot)$ satisfies a property that is slightly weaker than the Kurdyka-Lojasiewicz (KL) condition, denoted here as (KL'). It is shown that the iterations $J(\\boldsymbol{\\theta}_t)$ converge almost surely to"},"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":"2312.02828","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-12-05T15:22:39Z","cross_cats_sorted":["cs.LG","math.OC","math.PR"],"title_canon_sha256":"d7e17b8de06ac709b0ff3162fb50a5013042b4b866a2325b6989cb8c26cd458d","abstract_canon_sha256":"317c4344ffeaab8fe2611cfbbd7429cc081dd680b8bd83fe70a62a29aaf3a79c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:29.635621Z","signature_b64":"p7P9oT+rJWfsCHBzb+wyab5GSamL+AZ7wpCguRA0OdwaXl7+PXWqaiX0a9V27zgLeqDmx7hjmDihHA+ZvMeJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2bce33f18bb6533b473c279cf000d486ef95901a657871d02118bcde016194f","last_reissued_at":"2026-07-05T09:10:29.635129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:29.635129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence Rates for Stochastic Approximation: Biased Noise with Unbounded Variance, and Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.OC","math.PR"],"primary_cat":"stat.ML","authors_text":"M. Vidyasagar, Rajeeva L. Karandikar","submitted_at":"2023-12-05T15:22:39Z","abstract_excerpt":"In this paper, we study the convergence properties of the Stochastic Gradient Descent (SGD) method for finding a stationary point of a given objective function $J(\\cdot)$. The objective function is not required to be convex. Rather, our results apply to a class of ``invex'' functions, which have the property that every stationary point is also a global minimizer. First, it is assumed that $J(\\cdot)$ satisfies a property that is slightly weaker than the Kurdyka-Lojasiewicz (KL) condition, denoted here as (KL'). It is shown that the iterations $J(\\boldsymbol{\\theta}_t)$ converge almost surely to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02828","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/2312.02828/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":"2312.02828","created_at":"2026-07-05T09:10:29.635190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.02828v4","created_at":"2026-07-05T09:10:29.635190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02828","created_at":"2026-07-05T09:10:29.635190+00:00"},{"alias_kind":"pith_short_12","alias_value":"2K6OGPYYXNST","created_at":"2026-07-05T09:10:29.635190+00:00"},{"alias_kind":"pith_short_16","alias_value":"2K6OGPYYXNSTHNDT","created_at":"2026-07-05T09:10:29.635190+00:00"},{"alias_kind":"pith_short_8","alias_value":"2K6OGPYY","created_at":"2026-07-05T09:10:29.635190+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11904","citing_title":"Convergence of Momentum-Based Optimization Algorithms with Time-Varying Parameters","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2K6OGPYYXNSTHNDTYJ446AANJB","json":"https://pith.science/pith/2K6OGPYYXNSTHNDTYJ446AANJB.json","graph_json":"https://pith.science/api/pith-number/2K6OGPYYXNSTHNDTYJ446AANJB/graph.json","events_json":"https://pith.science/api/pith-number/2K6OGPYYXNSTHNDTYJ446AANJB/events.json","paper":"https://pith.science/paper/2K6OGPYY"},"agent_actions":{"view_html":"https://pith.science/pith/2K6OGPYYXNSTHNDTYJ446AANJB","download_json":"https://pith.science/pith/2K6OGPYYXNSTHNDTYJ446AANJB.json","view_paper":"https://pith.science/paper/2K6OGPYY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.02828&json=true","fetch_graph":"https://pith.science/api/pith-number/2K6OGPYYXNSTHNDTYJ446AANJB/graph.json","fetch_events":"https://pith.science/api/pith-number/2K6OGPYYXNSTHNDTYJ446AANJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2K6OGPYYXNSTHNDTYJ446AANJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2K6OGPYYXNSTHNDTYJ446AANJB/action/storage_attestation","attest_author":"https://pith.science/pith/2K6OGPYYXNSTHNDTYJ446AANJB/action/author_attestation","sign_citation":"https://pith.science/pith/2K6OGPYYXNSTHNDTYJ446AANJB/action/citation_signature","submit_replication":"https://pith.science/pith/2K6OGPYYXNSTHNDTYJ446AANJB/action/replication_record"}},"created_at":"2026-07-05T09:10:29.635190+00:00","updated_at":"2026-07-05T09:10:29.635190+00:00"}