{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OIGVJ3UTPQJJ44NPBSLM22QJUP","short_pith_number":"pith:OIGVJ3UT","schema_version":"1.0","canonical_sha256":"720d54ee937c129e71af0c96cd6a09a3dbbbd807adb9ef3c24d3732741525e2a","source":{"kind":"arxiv","id":"1802.05431","version":1},"attestation_state":"computed","paper":{"title":"On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Michael I. Jordan, Nicolas Flammarion, Niladri S. Chatterji, Peter L. Bartlett, Yi-An Ma","submitted_at":"2018-02-15T08:09:00Z","abstract_excerpt":"We provide convergence guarantees in Wasserstein distance for a variety of variance-reduction methods: SAGA Langevin diffusion, SVRG Langevin diffusion and control-variate underdamped Langevin diffusion. We analyze these methods under a uniform set of assumptions on the log-posterior distribution, assuming it to be smooth, strongly convex and Hessian Lipschitz. This is achieved by a new proof technique combining ideas from finite-sum optimization and the analysis of sampling methods. Our sharp theoretical bounds allow us to identify regimes of interest where each method performs better than th"},"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":"1802.05431","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-15T08:09:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0c06eeb82e5c160c41c5214c9ccc38a3f2a6e932eace7ea286ecf1df45d6c67f","abstract_canon_sha256":"f48094af3327e66f4044f97bef04d3f5558b07e4a72b588108f47faacf4983bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:15.705834Z","signature_b64":"e1lxb6wIWHpzsRjHB+kgOm+xmsU++nXQLt+SuUBDuZasoGhECMH+quFbj78m4hrMjgD1k27lJFcvLhlnlmFvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"720d54ee937c129e71af0c96cd6a09a3dbbbd807adb9ef3c24d3732741525e2a","last_reissued_at":"2026-05-18T00:23:15.705270Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:15.705270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Michael I. Jordan, Nicolas Flammarion, Niladri S. Chatterji, Peter L. Bartlett, Yi-An Ma","submitted_at":"2018-02-15T08:09:00Z","abstract_excerpt":"We provide convergence guarantees in Wasserstein distance for a variety of variance-reduction methods: SAGA Langevin diffusion, SVRG Langevin diffusion and control-variate underdamped Langevin diffusion. We analyze these methods under a uniform set of assumptions on the log-posterior distribution, assuming it to be smooth, strongly convex and Hessian Lipschitz. This is achieved by a new proof technique combining ideas from finite-sum optimization and the analysis of sampling methods. Our sharp theoretical bounds allow us to identify regimes of interest where each method performs better than th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05431","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":"1802.05431","created_at":"2026-05-18T00:23:15.705373+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.05431v1","created_at":"2026-05-18T00:23:15.705373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05431","created_at":"2026-05-18T00:23:15.705373+00:00"},{"alias_kind":"pith_short_12","alias_value":"OIGVJ3UTPQJJ","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OIGVJ3UTPQJJ44NP","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OIGVJ3UT","created_at":"2026-05-18T12:32:43.782077+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/OIGVJ3UTPQJJ44NPBSLM22QJUP","json":"https://pith.science/pith/OIGVJ3UTPQJJ44NPBSLM22QJUP.json","graph_json":"https://pith.science/api/pith-number/OIGVJ3UTPQJJ44NPBSLM22QJUP/graph.json","events_json":"https://pith.science/api/pith-number/OIGVJ3UTPQJJ44NPBSLM22QJUP/events.json","paper":"https://pith.science/paper/OIGVJ3UT"},"agent_actions":{"view_html":"https://pith.science/pith/OIGVJ3UTPQJJ44NPBSLM22QJUP","download_json":"https://pith.science/pith/OIGVJ3UTPQJJ44NPBSLM22QJUP.json","view_paper":"https://pith.science/paper/OIGVJ3UT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.05431&json=true","fetch_graph":"https://pith.science/api/pith-number/OIGVJ3UTPQJJ44NPBSLM22QJUP/graph.json","fetch_events":"https://pith.science/api/pith-number/OIGVJ3UTPQJJ44NPBSLM22QJUP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OIGVJ3UTPQJJ44NPBSLM22QJUP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OIGVJ3UTPQJJ44NPBSLM22QJUP/action/storage_attestation","attest_author":"https://pith.science/pith/OIGVJ3UTPQJJ44NPBSLM22QJUP/action/author_attestation","sign_citation":"https://pith.science/pith/OIGVJ3UTPQJJ44NPBSLM22QJUP/action/citation_signature","submit_replication":"https://pith.science/pith/OIGVJ3UTPQJJ44NPBSLM22QJUP/action/replication_record"}},"created_at":"2026-05-18T00:23:15.705373+00:00","updated_at":"2026-05-18T00:23:15.705373+00:00"}