{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CBPVPP4UV4B3SGGT52G7NARJIN","short_pith_number":"pith:CBPVPP4U","schema_version":"1.0","canonical_sha256":"105f57bf94af03b918d3ee8df68229435ceb5bdce1110a4a1655dbad97398a97","source":{"kind":"arxiv","id":"2405.16644","version":2},"attestation_state":"computed","paper":{"title":"Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","math.PR","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Alexey Naumov, Eric Moulines, Qi-Man Shao, Sergey Samsonov, Zhuo-Song Zhang","submitted_at":"2024-05-26T17:43:30Z","abstract_excerpt":"In this paper, we obtain the Berry-Esseen bound for multivariate normal approximation for the Polyak-Ruppert averaged iterates of the linear stochastic approximation (LSA) algorithm with decreasing step size. Moreover, we prove the non-asymptotic validity of the confidence intervals for parameter estimation with LSA based on multiplier bootstrap. This procedure updates the LSA estimate together with a set of randomly perturbed LSA estimates upon the arrival of subsequent observations. We illustrate our findings in the setting of temporal difference learning with linear function approximation."},"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":"2405.16644","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-05-26T17:43:30Z","cross_cats_sorted":["cs.LG","math.OC","math.PR","math.ST","stat.TH"],"title_canon_sha256":"076f62a424811c5da1577c2cc4b8967c7d9d3e11569a9ac7594658b9f42a09f5","abstract_canon_sha256":"55db0d6d26a336994e11ef58148e84385d6f2bb177b0274eccfc553036aba9ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:17.248362Z","signature_b64":"Fs0N2uY5ddkCBf1l0i1n4emX7k7PS23OnTg7svNISJFbjaQjM7o9idpC6OGSQhiL66JKvkaKpjLyjZfpdMG1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"105f57bf94af03b918d3ee8df68229435ceb5bdce1110a4a1655dbad97398a97","last_reissued_at":"2026-07-05T10:08:17.247943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:17.247943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","math.PR","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Alexey Naumov, Eric Moulines, Qi-Man Shao, Sergey Samsonov, Zhuo-Song Zhang","submitted_at":"2024-05-26T17:43:30Z","abstract_excerpt":"In this paper, we obtain the Berry-Esseen bound for multivariate normal approximation for the Polyak-Ruppert averaged iterates of the linear stochastic approximation (LSA) algorithm with decreasing step size. Moreover, we prove the non-asymptotic validity of the confidence intervals for parameter estimation with LSA based on multiplier bootstrap. This procedure updates the LSA estimate together with a set of randomly perturbed LSA estimates upon the arrival of subsequent observations. We illustrate our findings in the setting of temporal difference learning with linear function approximation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16644","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/2405.16644/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":"2405.16644","created_at":"2026-07-05T10:08:17.247998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16644v2","created_at":"2026-07-05T10:08:17.247998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16644","created_at":"2026-07-05T10:08:17.247998+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBPVPP4UV4B3","created_at":"2026-07-05T10:08:17.247998+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBPVPP4UV4B3SGGT","created_at":"2026-07-05T10:08:17.247998+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBPVPP4U","created_at":"2026-07-05T10:08:17.247998+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10814","citing_title":"Online Covariance Estimation in Averaged SGD: Improved Batch-Mean Rates and Minimax Optimality via Trajectory Regression","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBPVPP4UV4B3SGGT52G7NARJIN","json":"https://pith.science/pith/CBPVPP4UV4B3SGGT52G7NARJIN.json","graph_json":"https://pith.science/api/pith-number/CBPVPP4UV4B3SGGT52G7NARJIN/graph.json","events_json":"https://pith.science/api/pith-number/CBPVPP4UV4B3SGGT52G7NARJIN/events.json","paper":"https://pith.science/paper/CBPVPP4U"},"agent_actions":{"view_html":"https://pith.science/pith/CBPVPP4UV4B3SGGT52G7NARJIN","download_json":"https://pith.science/pith/CBPVPP4UV4B3SGGT52G7NARJIN.json","view_paper":"https://pith.science/paper/CBPVPP4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16644&json=true","fetch_graph":"https://pith.science/api/pith-number/CBPVPP4UV4B3SGGT52G7NARJIN/graph.json","fetch_events":"https://pith.science/api/pith-number/CBPVPP4UV4B3SGGT52G7NARJIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBPVPP4UV4B3SGGT52G7NARJIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBPVPP4UV4B3SGGT52G7NARJIN/action/storage_attestation","attest_author":"https://pith.science/pith/CBPVPP4UV4B3SGGT52G7NARJIN/action/author_attestation","sign_citation":"https://pith.science/pith/CBPVPP4UV4B3SGGT52G7NARJIN/action/citation_signature","submit_replication":"https://pith.science/pith/CBPVPP4UV4B3SGGT52G7NARJIN/action/replication_record"}},"created_at":"2026-07-05T10:08:17.247998+00:00","updated_at":"2026-07-05T10:08:17.247998+00:00"}