{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:PT3M4ET4HA27P7TV5OSAUPHOJB","short_pith_number":"pith:PT3M4ET4","schema_version":"1.0","canonical_sha256":"7cf6ce127c3835f7fe75eba40a3cee4841cfa3503201d8a458ebedf8a39ca119","source":{"kind":"arxiv","id":"1501.00438","version":2},"attestation_state":"computed","paper":{"title":"(Non-) asymptotic properties of Stochastic Gradient Langevin Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"stat.ME","authors_text":"and Yee Whye Teh, Konstantinos C. Zygalakis, Sebastian J. Vollmer","submitted_at":"2015-01-02T17:18:56Z","abstract_excerpt":"Applying standard Markov chain Monte Carlo (MCMC) algorithms to large data sets is computationally infeasible. The recently proposed stochastic gradient Langevin dynamics (SGLD) method circumvents this problem in three ways: it generates proposed moves using only a subset of the data, it skips the Metropolis-Hastings accept-reject step, and it uses sequences of decreasing step sizes. In \\cite{TehThierryVollmerSGLD2014}, we provided the mathematical foundations for the decreasing step size SGLD, including consistency and a central limit theorem. However, in practice the SGLD is run for a relati"},"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":"1501.00438","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2015-01-02T17:18:56Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"1651cb3bfd01b97dfa6b1270c749541fac89485d4f454c7fbb8ab8a091d91d9a","abstract_canon_sha256":"b7fac6e570e7c9b0d97cf883b43beebbdaaf3b8627827638ebeaff999fec1156"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:32:37.445337Z","signature_b64":"VnZxjex5gvQBJftOybTC8nkEhOtjQt8YbqGK+8WEyn/VRMLFNKy2vuEtun8s5wDCU5BZIngnXnrp/3Z6P0aUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cf6ce127c3835f7fe75eba40a3cee4841cfa3503201d8a458ebedf8a39ca119","last_reissued_at":"2026-05-18T01:32:37.444555Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:32:37.444555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"(Non-) asymptotic properties of Stochastic Gradient Langevin Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"stat.ME","authors_text":"and Yee Whye Teh, Konstantinos C. Zygalakis, Sebastian J. Vollmer","submitted_at":"2015-01-02T17:18:56Z","abstract_excerpt":"Applying standard Markov chain Monte Carlo (MCMC) algorithms to large data sets is computationally infeasible. The recently proposed stochastic gradient Langevin dynamics (SGLD) method circumvents this problem in three ways: it generates proposed moves using only a subset of the data, it skips the Metropolis-Hastings accept-reject step, and it uses sequences of decreasing step sizes. In \\cite{TehThierryVollmerSGLD2014}, we provided the mathematical foundations for the decreasing step size SGLD, including consistency and a central limit theorem. However, in practice the SGLD is run for a relati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.00438","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":""},"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":"1501.00438","created_at":"2026-05-18T01:32:37.444689+00:00"},{"alias_kind":"arxiv_version","alias_value":"1501.00438v2","created_at":"2026-05-18T01:32:37.444689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.00438","created_at":"2026-05-18T01:32:37.444689+00:00"},{"alias_kind":"pith_short_12","alias_value":"PT3M4ET4HA27","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_16","alias_value":"PT3M4ET4HA27P7TV","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_8","alias_value":"PT3M4ET4","created_at":"2026-05-18T12:29:37.295048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06599","citing_title":"Weight-Decay Turns Transformer Loss Landscapes Villani: Functional-Analytic Foundations for Optimization and Generalization","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PT3M4ET4HA27P7TV5OSAUPHOJB","json":"https://pith.science/pith/PT3M4ET4HA27P7TV5OSAUPHOJB.json","graph_json":"https://pith.science/api/pith-number/PT3M4ET4HA27P7TV5OSAUPHOJB/graph.json","events_json":"https://pith.science/api/pith-number/PT3M4ET4HA27P7TV5OSAUPHOJB/events.json","paper":"https://pith.science/paper/PT3M4ET4"},"agent_actions":{"view_html":"https://pith.science/pith/PT3M4ET4HA27P7TV5OSAUPHOJB","download_json":"https://pith.science/pith/PT3M4ET4HA27P7TV5OSAUPHOJB.json","view_paper":"https://pith.science/paper/PT3M4ET4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1501.00438&json=true","fetch_graph":"https://pith.science/api/pith-number/PT3M4ET4HA27P7TV5OSAUPHOJB/graph.json","fetch_events":"https://pith.science/api/pith-number/PT3M4ET4HA27P7TV5OSAUPHOJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PT3M4ET4HA27P7TV5OSAUPHOJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PT3M4ET4HA27P7TV5OSAUPHOJB/action/storage_attestation","attest_author":"https://pith.science/pith/PT3M4ET4HA27P7TV5OSAUPHOJB/action/author_attestation","sign_citation":"https://pith.science/pith/PT3M4ET4HA27P7TV5OSAUPHOJB/action/citation_signature","submit_replication":"https://pith.science/pith/PT3M4ET4HA27P7TV5OSAUPHOJB/action/replication_record"}},"created_at":"2026-05-18T01:32:37.444689+00:00","updated_at":"2026-05-18T01:32:37.444689+00:00"}