{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SQJ7HXXAEU7RACH5JLCM3WY6FJ","short_pith_number":"pith:SQJ7HXXA","schema_version":"1.0","canonical_sha256":"9413f3dee0253f1008fd4ac4cddb1e2a6fb873e9abc90bd74e067ec64b41dbc3","source":{"kind":"arxiv","id":"2112.12770","version":2},"attestation_state":"computed","paper":{"title":"Optimal and instance-dependent guarantees for Markovian linear stochastic approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR","math.ST","stat.ML","stat.TH"],"primary_cat":"math.OC","authors_text":"Ashwin Pananjady, Martin J. Wainwright, Peter L. Bartlett, Wenlong Mou","submitted_at":"2021-12-23T18:47:50Z","abstract_excerpt":"We study stochastic approximation procedures for approximately solving a $d$-dimensional linear fixed point equation based on observing a trajectory of length $n$ from an ergodic Markov chain. We first exhibit a non-asymptotic bound of the order $t_{\\mathrm{mix}} \\tfrac{d}{n}$ on the squared error of the last iterate of a standard scheme, where $t_{\\mathrm{mix}}$ is a mixing time. We then prove a non-asymptotic instance-dependent bound on a suitably averaged sequence of iterates, with a leading term that matches the local asymptotic minimax limit, including sharp dependence on the parameters $"},"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":"2112.12770","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-12-23T18:47:50Z","cross_cats_sorted":["cs.LG","math.PR","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"b06ebb98a89c9439ddb191d9e0d6c98f26966870bb0210577069050888736776","abstract_canon_sha256":"3c86b363034e3564cbf0e178ac667589c21c2a65208d5e992dbe6d0437c4b584"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:54.079773Z","signature_b64":"NV7/U+LW8LwLa8A6NabINbRRONes26qm1OPlBvEVs6HLSCCnL8xKk56ywAyC2WDyvTzaCm/DourntSRayk6wDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9413f3dee0253f1008fd4ac4cddb1e2a6fb873e9abc90bd74e067ec64b41dbc3","last_reissued_at":"2026-07-05T08:17:54.079340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:54.079340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal and instance-dependent guarantees for Markovian linear stochastic approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR","math.ST","stat.ML","stat.TH"],"primary_cat":"math.OC","authors_text":"Ashwin Pananjady, Martin J. Wainwright, Peter L. Bartlett, Wenlong Mou","submitted_at":"2021-12-23T18:47:50Z","abstract_excerpt":"We study stochastic approximation procedures for approximately solving a $d$-dimensional linear fixed point equation based on observing a trajectory of length $n$ from an ergodic Markov chain. We first exhibit a non-asymptotic bound of the order $t_{\\mathrm{mix}} \\tfrac{d}{n}$ on the squared error of the last iterate of a standard scheme, where $t_{\\mathrm{mix}}$ is a mixing time. We then prove a non-asymptotic instance-dependent bound on a suitably averaged sequence of iterates, with a leading term that matches the local asymptotic minimax limit, including sharp dependence on the parameters $"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.12770","kind":"arxiv","version":2},"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/2112.12770/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":"2112.12770","created_at":"2026-07-05T08:17:54.079399+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.12770v2","created_at":"2026-07-05T08:17:54.079399+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.12770","created_at":"2026-07-05T08:17:54.079399+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQJ7HXXAEU7R","created_at":"2026-07-05T08:17:54.079399+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQJ7HXXAEU7RACH5","created_at":"2026-07-05T08:17:54.079399+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQJ7HXXA","created_at":"2026-07-05T08:17:54.079399+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19102","citing_title":"Statistical inference for Linear Stochastic Approximation with Markovian Noise","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SQJ7HXXAEU7RACH5JLCM3WY6FJ","json":"https://pith.science/pith/SQJ7HXXAEU7RACH5JLCM3WY6FJ.json","graph_json":"https://pith.science/api/pith-number/SQJ7HXXAEU7RACH5JLCM3WY6FJ/graph.json","events_json":"https://pith.science/api/pith-number/SQJ7HXXAEU7RACH5JLCM3WY6FJ/events.json","paper":"https://pith.science/paper/SQJ7HXXA"},"agent_actions":{"view_html":"https://pith.science/pith/SQJ7HXXAEU7RACH5JLCM3WY6FJ","download_json":"https://pith.science/pith/SQJ7HXXAEU7RACH5JLCM3WY6FJ.json","view_paper":"https://pith.science/paper/SQJ7HXXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.12770&json=true","fetch_graph":"https://pith.science/api/pith-number/SQJ7HXXAEU7RACH5JLCM3WY6FJ/graph.json","fetch_events":"https://pith.science/api/pith-number/SQJ7HXXAEU7RACH5JLCM3WY6FJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQJ7HXXAEU7RACH5JLCM3WY6FJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQJ7HXXAEU7RACH5JLCM3WY6FJ/action/storage_attestation","attest_author":"https://pith.science/pith/SQJ7HXXAEU7RACH5JLCM3WY6FJ/action/author_attestation","sign_citation":"https://pith.science/pith/SQJ7HXXAEU7RACH5JLCM3WY6FJ/action/citation_signature","submit_replication":"https://pith.science/pith/SQJ7HXXAEU7RACH5JLCM3WY6FJ/action/replication_record"}},"created_at":"2026-07-05T08:17:54.079399+00:00","updated_at":"2026-07-05T08:17:54.079399+00:00"}