{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:2EMZZR6BNLIGQZTLVCF3NJ33GJ","short_pith_number":"pith:2EMZZR6B","schema_version":"1.0","canonical_sha256":"d1199cc7c16ad068666ba88bb6a77b32432ba5b87fea5b7beb2b044bc5bda4b5","source":{"kind":"arxiv","id":"1510.07727","version":7},"attestation_state":"computed","paper":{"title":"Statistically efficient thinning of a Markov chain sampler","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"stat.CO","authors_text":"Art B. Owen","submitted_at":"2015-10-27T00:00:54Z","abstract_excerpt":"It is common to subsample Markov chain output to reduce the storage burden. Geyer (1992) shows that discarding $k-1$ out of every $k$ observations will not improve statistical efficiency, as quantified through variance in a given computational budget. That observation is often taken to mean that thinning MCMC output cannot improve statistical efficiency. Here we suppose that it costs one unit of time to advance a Markov chain and then $\\theta>0$ units of time to compute a sampled quantity of interest. For a thinned process, that cost $\\theta$ is incurred less often, so it can be advanced throu"},"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":"1510.07727","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2015-10-27T00:00:54Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"43d33c7aa91d6d2400c6effa9c65a711e0a6919f7aa028dc27ef332f40d86df3","abstract_canon_sha256":"3cb65a6dba21ba40e8ebe50db663342c92faca100f46e4353e92e072a53b40fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:43.087362Z","signature_b64":"oGCsZuRrpwha6tvu/LEXBPexExK1i0ly4IYLM8QIy1Puxher7FPoNkbEq2Jm8n3xO9OnjlFsF/S/LAsmgCL4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1199cc7c16ad068666ba88bb6a77b32432ba5b87fea5b7beb2b044bc5bda4b5","last_reissued_at":"2026-05-18T00:46:43.086741Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:43.086741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistically efficient thinning of a Markov chain sampler","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"stat.CO","authors_text":"Art B. Owen","submitted_at":"2015-10-27T00:00:54Z","abstract_excerpt":"It is common to subsample Markov chain output to reduce the storage burden. Geyer (1992) shows that discarding $k-1$ out of every $k$ observations will not improve statistical efficiency, as quantified through variance in a given computational budget. That observation is often taken to mean that thinning MCMC output cannot improve statistical efficiency. Here we suppose that it costs one unit of time to advance a Markov chain and then $\\theta>0$ units of time to compute a sampled quantity of interest. For a thinned process, that cost $\\theta$ is incurred less often, so it can be advanced throu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.07727","kind":"arxiv","version":7},"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":"1510.07727","created_at":"2026-05-18T00:46:43.086818+00:00"},{"alias_kind":"arxiv_version","alias_value":"1510.07727v7","created_at":"2026-05-18T00:46:43.086818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.07727","created_at":"2026-05-18T00:46:43.086818+00:00"},{"alias_kind":"pith_short_12","alias_value":"2EMZZR6BNLIG","created_at":"2026-05-18T12:28:59.999130+00:00"},{"alias_kind":"pith_short_16","alias_value":"2EMZZR6BNLIGQZTL","created_at":"2026-05-18T12:28:59.999130+00:00"},{"alias_kind":"pith_short_8","alias_value":"2EMZZR6B","created_at":"2026-05-18T12:28:59.999130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.10600","citing_title":"Weighted quantization using MMD: From mean field to mean shift via gradient flows","ref_index":72,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2EMZZR6BNLIGQZTLVCF3NJ33GJ","json":"https://pith.science/pith/2EMZZR6BNLIGQZTLVCF3NJ33GJ.json","graph_json":"https://pith.science/api/pith-number/2EMZZR6BNLIGQZTLVCF3NJ33GJ/graph.json","events_json":"https://pith.science/api/pith-number/2EMZZR6BNLIGQZTLVCF3NJ33GJ/events.json","paper":"https://pith.science/paper/2EMZZR6B"},"agent_actions":{"view_html":"https://pith.science/pith/2EMZZR6BNLIGQZTLVCF3NJ33GJ","download_json":"https://pith.science/pith/2EMZZR6BNLIGQZTLVCF3NJ33GJ.json","view_paper":"https://pith.science/paper/2EMZZR6B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1510.07727&json=true","fetch_graph":"https://pith.science/api/pith-number/2EMZZR6BNLIGQZTLVCF3NJ33GJ/graph.json","fetch_events":"https://pith.science/api/pith-number/2EMZZR6BNLIGQZTLVCF3NJ33GJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2EMZZR6BNLIGQZTLVCF3NJ33GJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2EMZZR6BNLIGQZTLVCF3NJ33GJ/action/storage_attestation","attest_author":"https://pith.science/pith/2EMZZR6BNLIGQZTLVCF3NJ33GJ/action/author_attestation","sign_citation":"https://pith.science/pith/2EMZZR6BNLIGQZTLVCF3NJ33GJ/action/citation_signature","submit_replication":"https://pith.science/pith/2EMZZR6BNLIGQZTLVCF3NJ33GJ/action/replication_record"}},"created_at":"2026-05-18T00:46:43.086818+00:00","updated_at":"2026-05-18T00:46:43.086818+00:00"}