{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:25ARY5IQN5LFV3ZYQGVPXADUAX","short_pith_number":"pith:25ARY5IQ","schema_version":"1.0","canonical_sha256":"d7411c75106f565aef3881aafb807405c8dbf2788a699c6e21de083d2cf80a04","source":{"kind":"arxiv","id":"2302.07690","version":2},"attestation_state":"computed","paper":{"title":"Online Statistical Inference for Nonlinear Stochastic Approximation with Markovian Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Jiadong Liang, Xiang Li, Zhihua Zhang","submitted_at":"2023-02-15T14:31:11Z","abstract_excerpt":"We study the statistical inference of nonlinear stochastic approximation algorithms utilizing a single trajectory of Markovian data. Our methodology has practical applications in various scenarios, such as Stochastic Gradient Descent (SGD) on autoregressive data and asynchronous Q-Learning. By utilizing the standard stochastic approximation (SA) framework to estimate the target parameter, we establish a functional central limit theorem for its partial-sum process, $\\boldsymbol{\\phi}_T$. To further support this theory, we provide a matching semiparametric efficient lower bound and a non-asympto"},"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":"2302.07690","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2023-02-15T14:31:11Z","cross_cats_sorted":["stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"262e11400426adc212dea0094d6b5999c91809cce0eb9042d49af7a7915ede24","abstract_canon_sha256":"e043636d4406abbaa9a1165d80d6d667b42c08d7c95d286ad3851cd1fe54e74b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:20.640130Z","signature_b64":"DEGgKBKN+wgYJ3EJrM1EQMk+/qpNr1bI2nHEZ5x8jDGWtYwgmUs7hNalWpPWXX90ggIjHLd18KfF8rvgAxBLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7411c75106f565aef3881aafb807405c8dbf2788a699c6e21de083d2cf80a04","last_reissued_at":"2026-07-05T05:43:20.639671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:20.639671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Statistical Inference for Nonlinear Stochastic Approximation with Markovian Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Jiadong Liang, Xiang Li, Zhihua Zhang","submitted_at":"2023-02-15T14:31:11Z","abstract_excerpt":"We study the statistical inference of nonlinear stochastic approximation algorithms utilizing a single trajectory of Markovian data. Our methodology has practical applications in various scenarios, such as Stochastic Gradient Descent (SGD) on autoregressive data and asynchronous Q-Learning. By utilizing the standard stochastic approximation (SA) framework to estimate the target parameter, we establish a functional central limit theorem for its partial-sum process, $\\boldsymbol{\\phi}_T$. To further support this theory, we provide a matching semiparametric efficient lower bound and a non-asympto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.07690","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/2302.07690/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":"2302.07690","created_at":"2026-07-05T05:43:20.639731+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.07690v2","created_at":"2026-07-05T05:43:20.639731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.07690","created_at":"2026-07-05T05:43:20.639731+00:00"},{"alias_kind":"pith_short_12","alias_value":"25ARY5IQN5LF","created_at":"2026-07-05T05:43:20.639731+00:00"},{"alias_kind":"pith_short_16","alias_value":"25ARY5IQN5LFV3ZY","created_at":"2026-07-05T05:43:20.639731+00:00"},{"alias_kind":"pith_short_8","alias_value":"25ARY5IQ","created_at":"2026-07-05T05:43:20.639731+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08444","citing_title":"Statistical Efficiency and Inference of Quantile Distributional Reinforcement Learning","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2401.03893","citing_title":"Finite-Time Decoupled Convergence in Nonlinear Two-Time-Scale Stochastic Approximation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03100","citing_title":"Berry-Esseen bounds for multivariate martingale difference sequences in the Kolmogorov distance","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/25ARY5IQN5LFV3ZYQGVPXADUAX","json":"https://pith.science/pith/25ARY5IQN5LFV3ZYQGVPXADUAX.json","graph_json":"https://pith.science/api/pith-number/25ARY5IQN5LFV3ZYQGVPXADUAX/graph.json","events_json":"https://pith.science/api/pith-number/25ARY5IQN5LFV3ZYQGVPXADUAX/events.json","paper":"https://pith.science/paper/25ARY5IQ"},"agent_actions":{"view_html":"https://pith.science/pith/25ARY5IQN5LFV3ZYQGVPXADUAX","download_json":"https://pith.science/pith/25ARY5IQN5LFV3ZYQGVPXADUAX.json","view_paper":"https://pith.science/paper/25ARY5IQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.07690&json=true","fetch_graph":"https://pith.science/api/pith-number/25ARY5IQN5LFV3ZYQGVPXADUAX/graph.json","fetch_events":"https://pith.science/api/pith-number/25ARY5IQN5LFV3ZYQGVPXADUAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25ARY5IQN5LFV3ZYQGVPXADUAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25ARY5IQN5LFV3ZYQGVPXADUAX/action/storage_attestation","attest_author":"https://pith.science/pith/25ARY5IQN5LFV3ZYQGVPXADUAX/action/author_attestation","sign_citation":"https://pith.science/pith/25ARY5IQN5LFV3ZYQGVPXADUAX/action/citation_signature","submit_replication":"https://pith.science/pith/25ARY5IQN5LFV3ZYQGVPXADUAX/action/replication_record"}},"created_at":"2026-07-05T05:43:20.639731+00:00","updated_at":"2026-07-05T05:43:20.639731+00:00"}