{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LMI2KAPQU7C44ISAXVQEW2TYMY","short_pith_number":"pith:LMI2KAPQ","schema_version":"1.0","canonical_sha256":"5b11a501f0a7c5ce2240bd604b6a78662b67c42416925ca63808f9d89b8c4560","source":{"kind":"arxiv","id":"2411.13711","version":1},"attestation_state":"computed","paper":{"title":"Almost Sure Convergence Rates and Concentration of Stochastic Approximation and Reinforcement Learning with Markovian Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Shangtong Zhang, Xiaochi Qian, Xinyu Liu, Zixuan Xie","submitted_at":"2024-11-20T21:09:09Z","abstract_excerpt":"This paper establishes the first almost sure convergence rate and the first maximal concentration bound with exponential tails for general contractive stochastic approximation algorithms with Markovian noise. As a corollary, we also obtain convergence rates in $L^p$. Key to our successes is a novel discretization of the mean ODE of stochastic approximation algorithms using intervals with diminishing (instead of constant) length. As applications, we provide the first almost sure convergence rate for $Q$-learning with Markovian samples without count-based learning rates. We also provide the firs"},"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":"2411.13711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T21:09:09Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"57927329d4e293b787a851cd7b91b029f19a457b5633f3a0bdce87e3b1969b88","abstract_canon_sha256":"ce33191d121079a5b48bc408702bc6869cffbfd932b76c09d53abc58155410bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:36.166864Z","signature_b64":"r2TKBr5UwD41HKs/wYhGwk2gP8SIL2dlG0fqFg+XVSvkwW6v5XyLPoIcT+691fzPp11FDI1KVfYa48HnulvyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b11a501f0a7c5ce2240bd604b6a78662b67c42416925ca63808f9d89b8c4560","last_reissued_at":"2026-07-05T09:38:36.166382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:36.166382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Almost Sure Convergence Rates and Concentration of Stochastic Approximation and Reinforcement Learning with Markovian Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Shangtong Zhang, Xiaochi Qian, Xinyu Liu, Zixuan Xie","submitted_at":"2024-11-20T21:09:09Z","abstract_excerpt":"This paper establishes the first almost sure convergence rate and the first maximal concentration bound with exponential tails for general contractive stochastic approximation algorithms with Markovian noise. As a corollary, we also obtain convergence rates in $L^p$. Key to our successes is a novel discretization of the mean ODE of stochastic approximation algorithms using intervals with diminishing (instead of constant) length. As applications, we provide the first almost sure convergence rate for $Q$-learning with Markovian samples without count-based learning rates. We also provide the firs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13711","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/2411.13711/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":"2411.13711","created_at":"2026-07-05T09:38:36.166443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13711v1","created_at":"2026-07-05T09:38:36.166443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13711","created_at":"2026-07-05T09:38:36.166443+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMI2KAPQU7C4","created_at":"2026-07-05T09:38:36.166443+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMI2KAPQU7C44ISA","created_at":"2026-07-05T09:38:36.166443+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMI2KAPQ","created_at":"2026-07-05T09:38:36.166443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00309","citing_title":"Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31309","citing_title":"Non-Asymptotic Convergence of Stochastic Iterative Algorithms: A Lyapunov Framework","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18743","citing_title":"From Set Convergence to Pointwise Convergence: Finite-Time Guarantees for Average-Reward Q-Learning with Adaptive Stepsizes","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20999","citing_title":"Concentration of General Stochastic Approximation Under Heavy-Tailed Markovian Noise","ref_index":189,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LMI2KAPQU7C44ISAXVQEW2TYMY","json":"https://pith.science/pith/LMI2KAPQU7C44ISAXVQEW2TYMY.json","graph_json":"https://pith.science/api/pith-number/LMI2KAPQU7C44ISAXVQEW2TYMY/graph.json","events_json":"https://pith.science/api/pith-number/LMI2KAPQU7C44ISAXVQEW2TYMY/events.json","paper":"https://pith.science/paper/LMI2KAPQ"},"agent_actions":{"view_html":"https://pith.science/pith/LMI2KAPQU7C44ISAXVQEW2TYMY","download_json":"https://pith.science/pith/LMI2KAPQU7C44ISAXVQEW2TYMY.json","view_paper":"https://pith.science/paper/LMI2KAPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13711&json=true","fetch_graph":"https://pith.science/api/pith-number/LMI2KAPQU7C44ISAXVQEW2TYMY/graph.json","fetch_events":"https://pith.science/api/pith-number/LMI2KAPQU7C44ISAXVQEW2TYMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMI2KAPQU7C44ISAXVQEW2TYMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMI2KAPQU7C44ISAXVQEW2TYMY/action/storage_attestation","attest_author":"https://pith.science/pith/LMI2KAPQU7C44ISAXVQEW2TYMY/action/author_attestation","sign_citation":"https://pith.science/pith/LMI2KAPQU7C44ISAXVQEW2TYMY/action/citation_signature","submit_replication":"https://pith.science/pith/LMI2KAPQU7C44ISAXVQEW2TYMY/action/replication_record"}},"created_at":"2026-07-05T09:38:36.166443+00:00","updated_at":"2026-07-05T09:38:36.166443+00:00"}