{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:B5EXMXUMAKPRV4C2NDEN6YSR6B","short_pith_number":"pith:B5EXMXUM","schema_version":"1.0","canonical_sha256":"0f49765e8c029f1af05a68c8df6251f04faa9ad6731ed84ca4330a964a28dff8","source":{"kind":"arxiv","id":"1912.05153","version":1},"attestation_state":"computed","paper":{"title":"Sampling for Bayesian Mixture Models: MCMC with Polynomial-Time Mixing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG","math.PR","stat.CO"],"primary_cat":"stat.ML","authors_text":"Martin J. Wainwright, Michael I. Jordan, Nhat Ho, Peter L. Bartlett, Wenlong Mou","submitted_at":"2019-12-11T07:48:49Z","abstract_excerpt":"We study the problem of sampling from the power posterior distribution in Bayesian Gaussian mixture models, a robust version of the classical posterior. This power posterior is known to be non-log-concave and multi-modal, which leads to exponential mixing times for some standard MCMC algorithms. We introduce and study the Reflected Metropolis-Hastings Random Walk (RMRW) algorithm for sampling. For symmetric two-component Gaussian mixtures, we prove that its mixing time is bounded as $d^{1.5}(d + \\Vert \\theta_{0} \\Vert^2)^{4.5}$ as long as the sample size $n$ is of the order $d (d + \\Vert \\thet"},"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":"1912.05153","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-11T07:48:49Z","cross_cats_sorted":["cs.DS","cs.LG","math.PR","stat.CO"],"title_canon_sha256":"37f107db47174a61c39e84307d83ba017a7ebc2f59caa407ee44a7e3113a3add","abstract_canon_sha256":"83f09e6978948994ae89f250cf3f74edf7a2237690e5df47138091f9e4e70476"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:25:32.780258Z","signature_b64":"T5RnW6/7g8Kz4dor1Pu16oxWxxFZTq5Au6XrUD0kD6zjiIiNeEGPbodijZ2i8faB/DQ/PK/HZ3mae1yJS8IUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f49765e8c029f1af05a68c8df6251f04faa9ad6731ed84ca4330a964a28dff8","last_reissued_at":"2026-07-05T00:25:32.779822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:25:32.779822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sampling for Bayesian Mixture Models: MCMC with Polynomial-Time Mixing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG","math.PR","stat.CO"],"primary_cat":"stat.ML","authors_text":"Martin J. Wainwright, Michael I. Jordan, Nhat Ho, Peter L. Bartlett, Wenlong Mou","submitted_at":"2019-12-11T07:48:49Z","abstract_excerpt":"We study the problem of sampling from the power posterior distribution in Bayesian Gaussian mixture models, a robust version of the classical posterior. This power posterior is known to be non-log-concave and multi-modal, which leads to exponential mixing times for some standard MCMC algorithms. We introduce and study the Reflected Metropolis-Hastings Random Walk (RMRW) algorithm for sampling. For symmetric two-component Gaussian mixtures, we prove that its mixing time is bounded as $d^{1.5}(d + \\Vert \\theta_{0} \\Vert^2)^{4.5}$ as long as the sample size $n$ is of the order $d (d + \\Vert \\thet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05153","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.05153/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1912.05153","created_at":"2026-07-05T00:25:32.779886+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.05153v1","created_at":"2026-07-05T00:25:32.779886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05153","created_at":"2026-07-05T00:25:32.779886+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5EXMXUMAKPR","created_at":"2026-07-05T00:25:32.779886+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5EXMXUMAKPRV4C2","created_at":"2026-07-05T00:25:32.779886+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5EXMXUM","created_at":"2026-07-05T00:25:32.779886+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.07999","citing_title":"Fast Mixing of Data Augmentation Algorithms: Bayesian Probit, Logit, and Lasso Regression","ref_index":77,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B5EXMXUMAKPRV4C2NDEN6YSR6B","json":"https://pith.science/pith/B5EXMXUMAKPRV4C2NDEN6YSR6B.json","graph_json":"https://pith.science/api/pith-number/B5EXMXUMAKPRV4C2NDEN6YSR6B/graph.json","events_json":"https://pith.science/api/pith-number/B5EXMXUMAKPRV4C2NDEN6YSR6B/events.json","paper":"https://pith.science/paper/B5EXMXUM"},"agent_actions":{"view_html":"https://pith.science/pith/B5EXMXUMAKPRV4C2NDEN6YSR6B","download_json":"https://pith.science/pith/B5EXMXUMAKPRV4C2NDEN6YSR6B.json","view_paper":"https://pith.science/paper/B5EXMXUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.05153&json=true","fetch_graph":"https://pith.science/api/pith-number/B5EXMXUMAKPRV4C2NDEN6YSR6B/graph.json","fetch_events":"https://pith.science/api/pith-number/B5EXMXUMAKPRV4C2NDEN6YSR6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5EXMXUMAKPRV4C2NDEN6YSR6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5EXMXUMAKPRV4C2NDEN6YSR6B/action/storage_attestation","attest_author":"https://pith.science/pith/B5EXMXUMAKPRV4C2NDEN6YSR6B/action/author_attestation","sign_citation":"https://pith.science/pith/B5EXMXUMAKPRV4C2NDEN6YSR6B/action/citation_signature","submit_replication":"https://pith.science/pith/B5EXMXUMAKPRV4C2NDEN6YSR6B/action/replication_record"}},"created_at":"2026-07-05T00:25:32.779886+00:00","updated_at":"2026-07-05T00:25:32.779886+00:00"}