{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2PN4PIYLW6TORC63QJLY52IKS7","short_pith_number":"pith:2PN4PIYL","schema_version":"1.0","canonical_sha256":"d3dbc7a30bb7a6e88bdb82578ee90a97e4d8a407cdac920a4d8a133ae6e033a2","source":{"kind":"arxiv","id":"2402.06173","version":3},"attestation_state":"computed","paper":{"title":"Comparison of parallel SMC and MCMC for Bayesian deep learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Brian T. Kirby, Joseph M. Lukens, Kody J.H. Law, Sanjaya Lohani, Thomas A. Searles, Xin Qiu, Xinzhu Liang","submitted_at":"2024-02-09T04:13:38Z","abstract_excerpt":"This work systematically compares parallel implementations of consistent (asymptotically unbiased) Bayesian deep learning algorithms: sequential Monte Carlo sampler (SMC$_\\parallel$) or Markov chain Monte Carlo (MCMC$_\\parallel$). We provide a proof of convergence for SMC$_\\parallel$ showing that it theoretically achieves the same level of convergence as a single monolithic SMC sampler, while the reduced communication lowers wall-clock time. It is well-known that the first samples from MCMC need to be discarded to eliminate initialization bias, and that the number of discarded samples must gro"},"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":"2402.06173","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-02-09T04:13:38Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"739b7301c98a898398e2eecb2cdea6d261707c8cc943212f58845e675aff2041","abstract_canon_sha256":"ae1765651870bbf983f4b9a4f3549970710ab1d59f0adaafed553c5327e06c16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:13.346600Z","signature_b64":"Y7SP8pCJ1tnXnvqPKPrqZcLPrRpndN5U7UbG+ggT2wuX5dYI5uDhouuhK647TZE1m/E4ew8VKO1v0IRKzb2MDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3dbc7a30bb7a6e88bdb82578ee90a97e4d8a407cdac920a4d8a133ae6e033a2","last_reissued_at":"2026-07-05T11:56:13.346100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:13.346100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparison of parallel SMC and MCMC for Bayesian deep learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Brian T. Kirby, Joseph M. Lukens, Kody J.H. Law, Sanjaya Lohani, Thomas A. Searles, Xin Qiu, Xinzhu Liang","submitted_at":"2024-02-09T04:13:38Z","abstract_excerpt":"This work systematically compares parallel implementations of consistent (asymptotically unbiased) Bayesian deep learning algorithms: sequential Monte Carlo sampler (SMC$_\\parallel$) or Markov chain Monte Carlo (MCMC$_\\parallel$). We provide a proof of convergence for SMC$_\\parallel$ showing that it theoretically achieves the same level of convergence as a single monolithic SMC sampler, while the reduced communication lowers wall-clock time. It is well-known that the first samples from MCMC need to be discarded to eliminate initialization bias, and that the number of discarded samples must gro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06173","kind":"arxiv","version":3},"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/2402.06173/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":"2402.06173","created_at":"2026-07-05T11:56:13.346159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.06173v3","created_at":"2026-07-05T11:56:13.346159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06173","created_at":"2026-07-05T11:56:13.346159+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PN4PIYLW6TO","created_at":"2026-07-05T11:56:13.346159+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PN4PIYLW6TORC63","created_at":"2026-07-05T11:56:13.346159+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PN4PIYL","created_at":"2026-07-05T11:56:13.346159+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.13585","citing_title":"Scalable Bayesian Monte Carlo: fast uncertainty estimation beyond deep ensembles","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PN4PIYLW6TORC63QJLY52IKS7","json":"https://pith.science/pith/2PN4PIYLW6TORC63QJLY52IKS7.json","graph_json":"https://pith.science/api/pith-number/2PN4PIYLW6TORC63QJLY52IKS7/graph.json","events_json":"https://pith.science/api/pith-number/2PN4PIYLW6TORC63QJLY52IKS7/events.json","paper":"https://pith.science/paper/2PN4PIYL"},"agent_actions":{"view_html":"https://pith.science/pith/2PN4PIYLW6TORC63QJLY52IKS7","download_json":"https://pith.science/pith/2PN4PIYLW6TORC63QJLY52IKS7.json","view_paper":"https://pith.science/paper/2PN4PIYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.06173&json=true","fetch_graph":"https://pith.science/api/pith-number/2PN4PIYLW6TORC63QJLY52IKS7/graph.json","fetch_events":"https://pith.science/api/pith-number/2PN4PIYLW6TORC63QJLY52IKS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PN4PIYLW6TORC63QJLY52IKS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PN4PIYLW6TORC63QJLY52IKS7/action/storage_attestation","attest_author":"https://pith.science/pith/2PN4PIYLW6TORC63QJLY52IKS7/action/author_attestation","sign_citation":"https://pith.science/pith/2PN4PIYLW6TORC63QJLY52IKS7/action/citation_signature","submit_replication":"https://pith.science/pith/2PN4PIYLW6TORC63QJLY52IKS7/action/replication_record"}},"created_at":"2026-07-05T11:56:13.346159+00:00","updated_at":"2026-07-05T11:56:13.346159+00:00"}