{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:Y4FKIJK45ZUM76Z27ONDIXGXE7","short_pith_number":"pith:Y4FKIJK4","schema_version":"1.0","canonical_sha256":"c70aa4255cee68cffb3afb9a345cd727c8bd71210cd3edfb2134856d86cae992","source":{"kind":"arxiv","id":"1404.4178","version":6},"attestation_state":"computed","paper":{"title":"Speeding Up MCMC by Efficient Data Subsampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO","stat.ML"],"primary_cat":"stat.ME","authors_text":"Matias Quiroz, Mattias Villani, Minh-Ngoc Tran, Robert Kohn","submitted_at":"2014-04-16T09:33:36Z","abstract_excerpt":"We propose Subsampling MCMC, a Markov Chain Monte Carlo (MCMC) framework where the likelihood function for $n$ observations is estimated from a random subset of $m$ observations. We introduce a highly efficient unbiased estimator of the log-likelihood based on control variates, such that the computing cost is much smaller than that of the full log-likelihood in standard MCMC. The likelihood estimate is bias-corrected and used in two dependent pseudo-marginal algorithms to sample from a perturbed posterior, for which we derive the asymptotic error with respect to $n$ and $m$, respectively. We p"},"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":"1404.4178","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2014-04-16T09:33:36Z","cross_cats_sorted":["stat.CO","stat.ML"],"title_canon_sha256":"e6ab8d8af611b8b8e6edd59662636e0e8b31f936f0bf3f23fa7216222c793e71","abstract_canon_sha256":"832faafe05a79c9d0282104ac58b0f5681f619320dd534d0701d39051b20a8eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:21.964414Z","signature_b64":"qvuXDfl5WXEht/gN13ajC6R6UcYbmOtByN6p9ooseXptGDiJ3wVqKwF9aOmLWNjnstz2UXZMQbwc3xLv9WKFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c70aa4255cee68cffb3afb9a345cd727c8bd71210cd3edfb2134856d86cae992","last_reissued_at":"2026-05-17T23:57:21.963801Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:21.963801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speeding Up MCMC by Efficient Data Subsampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO","stat.ML"],"primary_cat":"stat.ME","authors_text":"Matias Quiroz, Mattias Villani, Minh-Ngoc Tran, Robert Kohn","submitted_at":"2014-04-16T09:33:36Z","abstract_excerpt":"We propose Subsampling MCMC, a Markov Chain Monte Carlo (MCMC) framework where the likelihood function for $n$ observations is estimated from a random subset of $m$ observations. We introduce a highly efficient unbiased estimator of the log-likelihood based on control variates, such that the computing cost is much smaller than that of the full log-likelihood in standard MCMC. The likelihood estimate is bias-corrected and used in two dependent pseudo-marginal algorithms to sample from a perturbed posterior, for which we derive the asymptotic error with respect to $n$ and $m$, respectively. We p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1404.4178","kind":"arxiv","version":6},"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":"1404.4178","created_at":"2026-05-17T23:57:21.963905+00:00"},{"alias_kind":"arxiv_version","alias_value":"1404.4178v6","created_at":"2026-05-17T23:57:21.963905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1404.4178","created_at":"2026-05-17T23:57:21.963905+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y4FKIJK45ZUM","created_at":"2026-05-18T12:28:57.508820+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y4FKIJK45ZUM76Z2","created_at":"2026-05-18T12:28:57.508820+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y4FKIJK4","created_at":"2026-05-18T12:28:57.508820+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/Y4FKIJK45ZUM76Z27ONDIXGXE7","json":"https://pith.science/pith/Y4FKIJK45ZUM76Z27ONDIXGXE7.json","graph_json":"https://pith.science/api/pith-number/Y4FKIJK45ZUM76Z27ONDIXGXE7/graph.json","events_json":"https://pith.science/api/pith-number/Y4FKIJK45ZUM76Z27ONDIXGXE7/events.json","paper":"https://pith.science/paper/Y4FKIJK4"},"agent_actions":{"view_html":"https://pith.science/pith/Y4FKIJK45ZUM76Z27ONDIXGXE7","download_json":"https://pith.science/pith/Y4FKIJK45ZUM76Z27ONDIXGXE7.json","view_paper":"https://pith.science/paper/Y4FKIJK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1404.4178&json=true","fetch_graph":"https://pith.science/api/pith-number/Y4FKIJK45ZUM76Z27ONDIXGXE7/graph.json","fetch_events":"https://pith.science/api/pith-number/Y4FKIJK45ZUM76Z27ONDIXGXE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y4FKIJK45ZUM76Z27ONDIXGXE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y4FKIJK45ZUM76Z27ONDIXGXE7/action/storage_attestation","attest_author":"https://pith.science/pith/Y4FKIJK45ZUM76Z27ONDIXGXE7/action/author_attestation","sign_citation":"https://pith.science/pith/Y4FKIJK45ZUM76Z27ONDIXGXE7/action/citation_signature","submit_replication":"https://pith.science/pith/Y4FKIJK45ZUM76Z27ONDIXGXE7/action/replication_record"}},"created_at":"2026-05-17T23:57:21.963905+00:00","updated_at":"2026-05-17T23:57:21.963905+00:00"}