{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4I55PYB3U53RAVPAVQJLR27MZP","short_pith_number":"pith:4I55PYB3","schema_version":"1.0","canonical_sha256":"e23bd7e03ba7771055e0ac12b8ebeccbc4b41d3dba59323892e1acc1289f9ba8","source":{"kind":"arxiv","id":"1811.10072","version":1},"attestation_state":"computed","paper":{"title":"The promises and pitfalls of Stochastic Gradient Langevin Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alain Durmus, Eric Moulines, Nicolas Brosse","submitted_at":"2018-11-25T18:58:39Z","abstract_excerpt":"Stochastic Gradient Langevin Dynamics (SGLD) has emerged as a key MCMC algorithm for Bayesian learning from large scale datasets. While SGLD with decreasing step sizes converges weakly to the posterior distribution, the algorithm is often used with a constant step size in practice and has demonstrated successes in machine learning tasks. The current practice is to set the step size inversely proportional to $N$ where $N$ is the number of training samples. As $N$ becomes large, we show that the SGLD algorithm has an invariant probability measure which significantly departs from the target poste"},"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":"1811.10072","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-11-25T18:58:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a508c14b5a2466ed9ac102cfd9bfe865a6d94756ec3b686dee1910b99d7e3542","abstract_canon_sha256":"5caf1c4e644e621145acb58bde7a4644ddac7727f5feba0d6e7aca135288149d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:58.746753Z","signature_b64":"50HWQjk+NTU9cbf464ONchOJr1zZqc9ylfBmKDBL3bTzSozK5Ve1RGyKevQ4ji1pQBUTUrrrENHCw3xLZGnVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e23bd7e03ba7771055e0ac12b8ebeccbc4b41d3dba59323892e1acc1289f9ba8","last_reissued_at":"2026-05-17T23:59:58.746188Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:58.746188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The promises and pitfalls of Stochastic Gradient Langevin Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alain Durmus, Eric Moulines, Nicolas Brosse","submitted_at":"2018-11-25T18:58:39Z","abstract_excerpt":"Stochastic Gradient Langevin Dynamics (SGLD) has emerged as a key MCMC algorithm for Bayesian learning from large scale datasets. While SGLD with decreasing step sizes converges weakly to the posterior distribution, the algorithm is often used with a constant step size in practice and has demonstrated successes in machine learning tasks. The current practice is to set the step size inversely proportional to $N$ where $N$ is the number of training samples. As $N$ becomes large, we show that the SGLD algorithm has an invariant probability measure which significantly departs from the target poste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10072","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":""},"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":"1811.10072","created_at":"2026-05-17T23:59:58.746256+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.10072v1","created_at":"2026-05-17T23:59:58.746256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10072","created_at":"2026-05-17T23:59:58.746256+00:00"},{"alias_kind":"pith_short_12","alias_value":"4I55PYB3U53R","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4I55PYB3U53RAVPA","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4I55PYB3","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4I55PYB3U53RAVPAVQJLR27MZP","json":"https://pith.science/pith/4I55PYB3U53RAVPAVQJLR27MZP.json","graph_json":"https://pith.science/api/pith-number/4I55PYB3U53RAVPAVQJLR27MZP/graph.json","events_json":"https://pith.science/api/pith-number/4I55PYB3U53RAVPAVQJLR27MZP/events.json","paper":"https://pith.science/paper/4I55PYB3"},"agent_actions":{"view_html":"https://pith.science/pith/4I55PYB3U53RAVPAVQJLR27MZP","download_json":"https://pith.science/pith/4I55PYB3U53RAVPAVQJLR27MZP.json","view_paper":"https://pith.science/paper/4I55PYB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.10072&json=true","fetch_graph":"https://pith.science/api/pith-number/4I55PYB3U53RAVPAVQJLR27MZP/graph.json","fetch_events":"https://pith.science/api/pith-number/4I55PYB3U53RAVPAVQJLR27MZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4I55PYB3U53RAVPAVQJLR27MZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4I55PYB3U53RAVPAVQJLR27MZP/action/storage_attestation","attest_author":"https://pith.science/pith/4I55PYB3U53RAVPAVQJLR27MZP/action/author_attestation","sign_citation":"https://pith.science/pith/4I55PYB3U53RAVPAVQJLR27MZP/action/citation_signature","submit_replication":"https://pith.science/pith/4I55PYB3U53RAVPAVQJLR27MZP/action/replication_record"}},"created_at":"2026-05-17T23:59:58.746256+00:00","updated_at":"2026-05-17T23:59:58.746256+00:00"}