{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZKY7FSQYZBR6PLXA3LNHEBIB3E","short_pith_number":"pith:ZKY7FSQY","schema_version":"1.0","canonical_sha256":"cab1f2ca18c863e7aee0dada720501d933ad2051fdda01bb76244548ffe66156","source":{"kind":"arxiv","id":"2508.05570","version":1},"attestation_state":"computed","paper":{"title":"High-Order Error Bounds for Markovian LSA with Richardson-Romberg Extrapolation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Alexey Naumov, Ilya Levin, Sergey Samsonov","submitted_at":"2025-08-07T17:02:11Z","abstract_excerpt":"In this paper, we study the bias and high-order error bounds of the Linear Stochastic Approximation (LSA) algorithm with Polyak-Ruppert (PR) averaging under Markovian noise. We focus on the version of the algorithm with constant step size $\\alpha$ and propose a novel decomposition of the bias via a linearization technique. We analyze the structure of the bias and show that the leading-order term is linear in $\\alpha$ and cannot be eliminated by PR averaging. To address this, we apply the Richardson-Romberg (RR) extrapolation procedure, which effectively cancels the leading bias term. We derive"},"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":"2508.05570","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-08-07T17:02:11Z","cross_cats_sorted":["cs.LG","math.OC","math.ST","stat.TH"],"title_canon_sha256":"e2fccfb430cb2084c6b3ef2fe3d4fe77589dc3ee5053aa871118f45ad7220a97","abstract_canon_sha256":"b9dab9bde76ef9e00e96166f92ed79c04bf07723e13be49b6e76534a9f77bda4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:21.648878Z","signature_b64":"SerXa1wWf8KaZ+WyayaYVX9j4WcErz1PAKmKTMPQXY2WMrs9upQo6///McgqFCNatM4YRkLly69QJUTH9mGCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cab1f2ca18c863e7aee0dada720501d933ad2051fdda01bb76244548ffe66156","last_reissued_at":"2026-07-05T11:50:21.648346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:21.648346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Order Error Bounds for Markovian LSA with Richardson-Romberg Extrapolation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Alexey Naumov, Ilya Levin, Sergey Samsonov","submitted_at":"2025-08-07T17:02:11Z","abstract_excerpt":"In this paper, we study the bias and high-order error bounds of the Linear Stochastic Approximation (LSA) algorithm with Polyak-Ruppert (PR) averaging under Markovian noise. We focus on the version of the algorithm with constant step size $\\alpha$ and propose a novel decomposition of the bias via a linearization technique. We analyze the structure of the bias and show that the leading-order term is linear in $\\alpha$ and cannot be eliminated by PR averaging. To address this, we apply the Richardson-Romberg (RR) extrapolation procedure, which effectively cancels the leading bias term. We derive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05570","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/2508.05570/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":"2508.05570","created_at":"2026-07-05T11:50:21.648427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.05570v1","created_at":"2026-07-05T11:50:21.648427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05570","created_at":"2026-07-05T11:50:21.648427+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKY7FSQYZBR6","created_at":"2026-07-05T11:50:21.648427+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKY7FSQYZBR6PLXA","created_at":"2026-07-05T11:50:21.648427+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKY7FSQY","created_at":"2026-07-05T11:50:21.648427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13378","citing_title":"Revisiting the Constant Stepsize Stochastic Approximation with Decision-Dependent Markovian Noise","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKY7FSQYZBR6PLXA3LNHEBIB3E","json":"https://pith.science/pith/ZKY7FSQYZBR6PLXA3LNHEBIB3E.json","graph_json":"https://pith.science/api/pith-number/ZKY7FSQYZBR6PLXA3LNHEBIB3E/graph.json","events_json":"https://pith.science/api/pith-number/ZKY7FSQYZBR6PLXA3LNHEBIB3E/events.json","paper":"https://pith.science/paper/ZKY7FSQY"},"agent_actions":{"view_html":"https://pith.science/pith/ZKY7FSQYZBR6PLXA3LNHEBIB3E","download_json":"https://pith.science/pith/ZKY7FSQYZBR6PLXA3LNHEBIB3E.json","view_paper":"https://pith.science/paper/ZKY7FSQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.05570&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKY7FSQYZBR6PLXA3LNHEBIB3E/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKY7FSQYZBR6PLXA3LNHEBIB3E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKY7FSQYZBR6PLXA3LNHEBIB3E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKY7FSQYZBR6PLXA3LNHEBIB3E/action/storage_attestation","attest_author":"https://pith.science/pith/ZKY7FSQYZBR6PLXA3LNHEBIB3E/action/author_attestation","sign_citation":"https://pith.science/pith/ZKY7FSQYZBR6PLXA3LNHEBIB3E/action/citation_signature","submit_replication":"https://pith.science/pith/ZKY7FSQYZBR6PLXA3LNHEBIB3E/action/replication_record"}},"created_at":"2026-07-05T11:50:21.648427+00:00","updated_at":"2026-07-05T11:50:21.648427+00:00"}