{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KJK4NZM52VGNRRUUNIXUIR7BBK","short_pith_number":"pith:KJK4NZM5","schema_version":"1.0","canonical_sha256":"5255c6e59dd54cd8c6946a2f4447e10a99e625be062f0d67f9ce569d0613de20","source":{"kind":"arxiv","id":"2104.01627","version":1},"attestation_state":"computed","paper":{"title":"Finite-Time Convergence Rates of Nonlinear Two-Time-Scale Stochastic Approximation under Markovian Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Thinh T. Doan","submitted_at":"2021-04-04T15:19:19Z","abstract_excerpt":"We study the so-called two-time-scale stochastic approximation, a simulation-based approach for finding the roots of two coupled nonlinear operators. Our focus is to characterize its finite-time performance in a Markov setting, which often arises in stochastic control and reinforcement learning problems. In particular, we consider the scenario where the data in the method are generated by Markov processes, therefore, they are dependent. Such dependent data result to biased observations of the underlying operators. Under some fairly standard assumptions on the operators and the Markov processes"},"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":"2104.01627","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-04-04T15:19:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a1b8b65e3634b2fd80a18db393e9a82023af595581a6b7fb888a66d41b49ee4f","abstract_canon_sha256":"dcf2362a8e851ed194839947ca30c0138dc8fdddcc727b35e75f3974c9cbc856"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:02.058424Z","signature_b64":"EhLdw1Sc7jCWKAgcrQnfrhb5fOKZoAVomLcdkNtH/65VGQyXxQTWcqo47lNsl/gDcHh09c+R/0vnpeIZuMPMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5255c6e59dd54cd8c6946a2f4447e10a99e625be062f0d67f9ce569d0613de20","last_reissued_at":"2026-07-05T02:29:02.058021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:02.058021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finite-Time Convergence Rates of Nonlinear Two-Time-Scale Stochastic Approximation under Markovian Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Thinh T. Doan","submitted_at":"2021-04-04T15:19:19Z","abstract_excerpt":"We study the so-called two-time-scale stochastic approximation, a simulation-based approach for finding the roots of two coupled nonlinear operators. Our focus is to characterize its finite-time performance in a Markov setting, which often arises in stochastic control and reinforcement learning problems. In particular, we consider the scenario where the data in the method are generated by Markov processes, therefore, they are dependent. Such dependent data result to biased observations of the underlying operators. Under some fairly standard assumptions on the operators and the Markov processes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01627","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/2104.01627/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":"2104.01627","created_at":"2026-07-05T02:29:02.058075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.01627v1","created_at":"2026-07-05T02:29:02.058075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01627","created_at":"2026-07-05T02:29:02.058075+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJK4NZM52VGN","created_at":"2026-07-05T02:29:02.058075+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJK4NZM52VGNRRUU","created_at":"2026-07-05T02:29:02.058075+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJK4NZM5","created_at":"2026-07-05T02:29:02.058075+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.03893","citing_title":"Finite-Time Decoupled Convergence in Nonlinear Two-Time-Scale Stochastic Approximation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09946","citing_title":"Structure from Strategic Interaction & Uncertainty: Risk Sensitive Games for Robust Preference Learning","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09946","citing_title":"Structure from Strategic Interaction & Uncertainty: Risk Sensitive Games for Robust Preference Learning","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJK4NZM52VGNRRUUNIXUIR7BBK","json":"https://pith.science/pith/KJK4NZM52VGNRRUUNIXUIR7BBK.json","graph_json":"https://pith.science/api/pith-number/KJK4NZM52VGNRRUUNIXUIR7BBK/graph.json","events_json":"https://pith.science/api/pith-number/KJK4NZM52VGNRRUUNIXUIR7BBK/events.json","paper":"https://pith.science/paper/KJK4NZM5"},"agent_actions":{"view_html":"https://pith.science/pith/KJK4NZM52VGNRRUUNIXUIR7BBK","download_json":"https://pith.science/pith/KJK4NZM52VGNRRUUNIXUIR7BBK.json","view_paper":"https://pith.science/paper/KJK4NZM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.01627&json=true","fetch_graph":"https://pith.science/api/pith-number/KJK4NZM52VGNRRUUNIXUIR7BBK/graph.json","fetch_events":"https://pith.science/api/pith-number/KJK4NZM52VGNRRUUNIXUIR7BBK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJK4NZM52VGNRRUUNIXUIR7BBK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJK4NZM52VGNRRUUNIXUIR7BBK/action/storage_attestation","attest_author":"https://pith.science/pith/KJK4NZM52VGNRRUUNIXUIR7BBK/action/author_attestation","sign_citation":"https://pith.science/pith/KJK4NZM52VGNRRUUNIXUIR7BBK/action/citation_signature","submit_replication":"https://pith.science/pith/KJK4NZM52VGNRRUUNIXUIR7BBK/action/replication_record"}},"created_at":"2026-07-05T02:29:02.058075+00:00","updated_at":"2026-07-05T02:29:02.058075+00:00"}