{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:A5OWNPM5GTSDO26GLQIVK7ODCT","short_pith_number":"pith:A5OWNPM5","schema_version":"1.0","canonical_sha256":"075d66bd9d34e4376bc65c11557dc314e1f98a7f61ff640879e1042240f38b3f","source":{"kind":"arxiv","id":"1902.00629","version":4},"attestation_state":"computed","paper":{"title":"Non-asymptotic Analysis of Biased Stochastic Approximation Scheme","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Belhal Karimi, Blazej Miasojedow, Eric Moulines, Hoi-To Wai","submitted_at":"2019-02-02T02:45:49Z","abstract_excerpt":"Stochastic approximation (SA) is a key method used in statistical learning. Recently, its non-asymptotic convergence analysis has been considered in many papers. However, most of the prior analyses are made under restrictive assumptions such as unbiased gradient estimates and convex objective function, which significantly limit their applications to sophisticated tasks such as online and reinforcement learning. These restrictions are all essentially relaxed in this work. In particular, we analyze a general SA scheme to minimize a non-convex, smooth objective function. We consider update proced"},"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":"1902.00629","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2019-02-02T02:45:49Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"ebd116894d0dbc1c37d8c718c2c7825a28379b032a8d301e40d58a494a381981","abstract_canon_sha256":"90005a001d507ec2777c2509277d74d420e7ae3d01cbcba13dae44735c3ca137"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:16.835749Z","signature_b64":"UINpCsNcsyhFSbLJGZMLfikshs4N617q4s9fN4BWuGaXKouTAmyseRsRyyuBR6Yo2X1liKlBaI1ik2YjR7vpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"075d66bd9d34e4376bc65c11557dc314e1f98a7f61ff640879e1042240f38b3f","last_reissued_at":"2026-05-17T23:43:16.835093Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:16.835093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-asymptotic Analysis of Biased Stochastic Approximation Scheme","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Belhal Karimi, Blazej Miasojedow, Eric Moulines, Hoi-To Wai","submitted_at":"2019-02-02T02:45:49Z","abstract_excerpt":"Stochastic approximation (SA) is a key method used in statistical learning. Recently, its non-asymptotic convergence analysis has been considered in many papers. However, most of the prior analyses are made under restrictive assumptions such as unbiased gradient estimates and convex objective function, which significantly limit their applications to sophisticated tasks such as online and reinforcement learning. These restrictions are all essentially relaxed in this work. In particular, we analyze a general SA scheme to minimize a non-convex, smooth objective function. We consider update proced"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00629","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":""},"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":"1902.00629","created_at":"2026-05-17T23:43:16.835179+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.00629v4","created_at":"2026-05-17T23:43:16.835179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00629","created_at":"2026-05-17T23:43:16.835179+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5OWNPM5GTSD","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5OWNPM5GTSDO26G","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5OWNPM5","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A5OWNPM5GTSDO26GLQIVK7ODCT","json":"https://pith.science/pith/A5OWNPM5GTSDO26GLQIVK7ODCT.json","graph_json":"https://pith.science/api/pith-number/A5OWNPM5GTSDO26GLQIVK7ODCT/graph.json","events_json":"https://pith.science/api/pith-number/A5OWNPM5GTSDO26GLQIVK7ODCT/events.json","paper":"https://pith.science/paper/A5OWNPM5"},"agent_actions":{"view_html":"https://pith.science/pith/A5OWNPM5GTSDO26GLQIVK7ODCT","download_json":"https://pith.science/pith/A5OWNPM5GTSDO26GLQIVK7ODCT.json","view_paper":"https://pith.science/paper/A5OWNPM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.00629&json=true","fetch_graph":"https://pith.science/api/pith-number/A5OWNPM5GTSDO26GLQIVK7ODCT/graph.json","fetch_events":"https://pith.science/api/pith-number/A5OWNPM5GTSDO26GLQIVK7ODCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5OWNPM5GTSDO26GLQIVK7ODCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5OWNPM5GTSDO26GLQIVK7ODCT/action/storage_attestation","attest_author":"https://pith.science/pith/A5OWNPM5GTSDO26GLQIVK7ODCT/action/author_attestation","sign_citation":"https://pith.science/pith/A5OWNPM5GTSDO26GLQIVK7ODCT/action/citation_signature","submit_replication":"https://pith.science/pith/A5OWNPM5GTSDO26GLQIVK7ODCT/action/replication_record"}},"created_at":"2026-05-17T23:43:16.835179+00:00","updated_at":"2026-05-17T23:43:16.835179+00:00"}