{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5WVWP35DYUJ6IIL67OU6TNLXSA","short_pith_number":"pith:5WVWP35D","schema_version":"1.0","canonical_sha256":"edab67efa3c513e4217efba9e9b57790022d562aa80a76c68cb4d5d407d8621b","source":{"kind":"arxiv","id":"2303.10599","version":2},"attestation_state":"computed","paper":{"title":"Convergence Analysis of Stochastic Gradient Descent with MCMC Estimators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"stat.ML","authors_text":"Fan Chen, Huajie Chen, Tianyou Li, Zaiwen Wen","submitted_at":"2023-03-19T08:29:49Z","abstract_excerpt":"Understanding stochastic gradient descent (SGD) and its variants is essential for machine learning. However, most of the preceding analyses are conducted under amenable conditions such as unbiased gradient estimator and bounded objective functions, which does not encompass many sophisticated applications, such as variational Monte Carlo, entropy-regularized reinforcement learning and variational inference. In this paper, we consider the SGD algorithm that employ the Markov Chain Monte Carlo (MCMC) estimator to compute the gradient, called MCMC-SGD. Since MCMC reduces the sampling complexity si"},"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":"2303.10599","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-03-19T08:29:49Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"b3c679a2505f8a2a1b1ab2e34f8eab010f2e1e5c9ad6fe2d9e54ebc609313af6","abstract_canon_sha256":"e63afcb1fb2784f0ff15089047a89a9ef6a5baf6d874a098a2c3cebba452648b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:49.579689Z","signature_b64":"gGP0lvWCsm49s2Qv+EG5HtlAV9+82t6y5ubkazNa+HqUgPneL8CbQcb4OD7+G8efYINJFyRKhBPlNEeG79b6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edab67efa3c513e4217efba9e9b57790022d562aa80a76c68cb4d5d407d8621b","last_reissued_at":"2026-07-05T07:59:49.579157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:49.579157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence Analysis of Stochastic Gradient Descent with MCMC Estimators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"stat.ML","authors_text":"Fan Chen, Huajie Chen, Tianyou Li, Zaiwen Wen","submitted_at":"2023-03-19T08:29:49Z","abstract_excerpt":"Understanding stochastic gradient descent (SGD) and its variants is essential for machine learning. However, most of the preceding analyses are conducted under amenable conditions such as unbiased gradient estimator and bounded objective functions, which does not encompass many sophisticated applications, such as variational Monte Carlo, entropy-regularized reinforcement learning and variational inference. In this paper, we consider the SGD algorithm that employ the Markov Chain Monte Carlo (MCMC) estimator to compute the gradient, called MCMC-SGD. Since MCMC reduces the sampling complexity si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.10599","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/2303.10599/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":"2303.10599","created_at":"2026-07-05T07:59:49.579221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.10599v2","created_at":"2026-07-05T07:59:49.579221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.10599","created_at":"2026-07-05T07:59:49.579221+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WVWP35DYUJ6","created_at":"2026-07-05T07:59:49.579221+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WVWP35DYUJ6IIL6","created_at":"2026-07-05T07:59:49.579221+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WVWP35D","created_at":"2026-07-05T07:59:49.579221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26009","citing_title":"Is Variational Monte Carlo Robust? Sharp Moment Thresholds and Heavy-tailed Stochastic Optimization","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18357","citing_title":"Momentum Stability and Adaptive Control in Stochastic Reconfiguration","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WVWP35DYUJ6IIL67OU6TNLXSA","json":"https://pith.science/pith/5WVWP35DYUJ6IIL67OU6TNLXSA.json","graph_json":"https://pith.science/api/pith-number/5WVWP35DYUJ6IIL67OU6TNLXSA/graph.json","events_json":"https://pith.science/api/pith-number/5WVWP35DYUJ6IIL67OU6TNLXSA/events.json","paper":"https://pith.science/paper/5WVWP35D"},"agent_actions":{"view_html":"https://pith.science/pith/5WVWP35DYUJ6IIL67OU6TNLXSA","download_json":"https://pith.science/pith/5WVWP35DYUJ6IIL67OU6TNLXSA.json","view_paper":"https://pith.science/paper/5WVWP35D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.10599&json=true","fetch_graph":"https://pith.science/api/pith-number/5WVWP35DYUJ6IIL67OU6TNLXSA/graph.json","fetch_events":"https://pith.science/api/pith-number/5WVWP35DYUJ6IIL67OU6TNLXSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WVWP35DYUJ6IIL67OU6TNLXSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WVWP35DYUJ6IIL67OU6TNLXSA/action/storage_attestation","attest_author":"https://pith.science/pith/5WVWP35DYUJ6IIL67OU6TNLXSA/action/author_attestation","sign_citation":"https://pith.science/pith/5WVWP35DYUJ6IIL67OU6TNLXSA/action/citation_signature","submit_replication":"https://pith.science/pith/5WVWP35DYUJ6IIL67OU6TNLXSA/action/replication_record"}},"created_at":"2026-07-05T07:59:49.579221+00:00","updated_at":"2026-07-05T07:59:49.579221+00:00"}