{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5FOJLLMDDBSMC3DWDFRM2W5BZZ","short_pith_number":"pith:5FOJLLMD","schema_version":"1.0","canonical_sha256":"e95c95ad831864c16c761962cd5ba1ce79fbe22b37032da8d7275f59c6724286","source":{"kind":"arxiv","id":"2505.21796","version":1},"attestation_state":"computed","paper":{"title":"A General-Purpose Theorem for High-Probability Bounds of Stochastic Approximation with Polyak Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Martin Zubeldia, Sajad Khodadadian","submitted_at":"2025-05-27T21:58:35Z","abstract_excerpt":"Polyak-Ruppert averaging is a widely used technique to achieve the optimal asymptotic variance of stochastic approximation (SA) algorithms, yet its high-probability performance guarantees remain underexplored in general settings. In this paper, we present a general framework for establishing non-asymptotic concentration bounds for the error of averaged SA iterates. Our approach assumes access to individual concentration bounds for the unaveraged iterates and yields a sharp bound on the averaged iterates. We also construct an example, showing the tightness of our result up to constant multiplic"},"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":"2505.21796","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-27T21:58:35Z","cross_cats_sorted":["cs.LG","math.PR"],"title_canon_sha256":"387c55cc8c67d0356b58549af0f426296eddcaf4b630fd3be3918c6d3f523741","abstract_canon_sha256":"d74e26c859c4440794f714dd320763daf26adb176e641e8e9adce98bcd191f30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:03.750648Z","signature_b64":"IjY2wb6/uf1JJ9ub1oNN9oN/cRueBqapyJ9/nnNpdyUqgVkZNdYLZOpgHbqOJ6YL4x6caqie19Ihcz+HXIhRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e95c95ad831864c16c761962cd5ba1ce79fbe22b37032da8d7275f59c6724286","last_reissued_at":"2026-07-05T11:11:03.750191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:03.750191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A General-Purpose Theorem for High-Probability Bounds of Stochastic Approximation with Polyak Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Martin Zubeldia, Sajad Khodadadian","submitted_at":"2025-05-27T21:58:35Z","abstract_excerpt":"Polyak-Ruppert averaging is a widely used technique to achieve the optimal asymptotic variance of stochastic approximation (SA) algorithms, yet its high-probability performance guarantees remain underexplored in general settings. In this paper, we present a general framework for establishing non-asymptotic concentration bounds for the error of averaged SA iterates. Our approach assumes access to individual concentration bounds for the unaveraged iterates and yields a sharp bound on the averaged iterates. We also construct an example, showing the tightness of our result up to constant multiplic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21796","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/2505.21796/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":"2505.21796","created_at":"2026-07-05T11:11:03.750248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21796v1","created_at":"2026-07-05T11:11:03.750248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21796","created_at":"2026-07-05T11:11:03.750248+00:00"},{"alias_kind":"pith_short_12","alias_value":"5FOJLLMDDBSM","created_at":"2026-07-05T11:11:03.750248+00:00"},{"alias_kind":"pith_short_16","alias_value":"5FOJLLMDDBSMC3DW","created_at":"2026-07-05T11:11:03.750248+00:00"},{"alias_kind":"pith_short_8","alias_value":"5FOJLLMD","created_at":"2026-07-05T11:11:03.750248+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.18964","citing_title":"Central Limit Theorems for Asynchronous Averaged Q-Learning","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5FOJLLMDDBSMC3DWDFRM2W5BZZ","json":"https://pith.science/pith/5FOJLLMDDBSMC3DWDFRM2W5BZZ.json","graph_json":"https://pith.science/api/pith-number/5FOJLLMDDBSMC3DWDFRM2W5BZZ/graph.json","events_json":"https://pith.science/api/pith-number/5FOJLLMDDBSMC3DWDFRM2W5BZZ/events.json","paper":"https://pith.science/paper/5FOJLLMD"},"agent_actions":{"view_html":"https://pith.science/pith/5FOJLLMDDBSMC3DWDFRM2W5BZZ","download_json":"https://pith.science/pith/5FOJLLMDDBSMC3DWDFRM2W5BZZ.json","view_paper":"https://pith.science/paper/5FOJLLMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21796&json=true","fetch_graph":"https://pith.science/api/pith-number/5FOJLLMDDBSMC3DWDFRM2W5BZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5FOJLLMDDBSMC3DWDFRM2W5BZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5FOJLLMDDBSMC3DWDFRM2W5BZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5FOJLLMDDBSMC3DWDFRM2W5BZZ/action/storage_attestation","attest_author":"https://pith.science/pith/5FOJLLMDDBSMC3DWDFRM2W5BZZ/action/author_attestation","sign_citation":"https://pith.science/pith/5FOJLLMDDBSMC3DWDFRM2W5BZZ/action/citation_signature","submit_replication":"https://pith.science/pith/5FOJLLMDDBSMC3DWDFRM2W5BZZ/action/replication_record"}},"created_at":"2026-07-05T11:11:03.750248+00:00","updated_at":"2026-07-05T11:11:03.750248+00:00"}