{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YV6KEM4RN43ZKCJ32IFTJYBUJI","short_pith_number":"pith:YV6KEM4R","schema_version":"1.0","canonical_sha256":"c57ca233916f3795093bd20b34e0344a24ddce89e0989b09c414c37c2d833712","source":{"kind":"arxiv","id":"1905.04062","version":2},"attestation_state":"computed","paper":{"title":"A Contrastive Divergence for Combining Variational Inference and MCMC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Francisco J. R. Ruiz, Michalis K. Titsias","submitted_at":"2019-05-10T10:45:23Z","abstract_excerpt":"We develop a method to combine Markov chain Monte Carlo (MCMC) and variational inference (VI), leveraging the advantages of both inference approaches. Specifically, we improve the variational distribution by running a few MCMC steps. To make inference tractable, we introduce the variational contrastive divergence (VCD), a new divergence that replaces the standard Kullback-Leibler (KL) divergence used in VI. The VCD captures a notion of discrepancy between the initial variational distribution and its improved version (obtained after running the MCMC steps), and it converges asymptotically to 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":"1905.04062","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-10T10:45:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"25edf4b12aa4ce154ad2ebe9090c56c024bc56172d300e31a95d23734e7b867e","abstract_canon_sha256":"f3502e829fca98d969562baa3671c3d8a5885e07e5916be0b9709207b5df9029"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:53.952302Z","signature_b64":"J+skBgXQ/OnW1lMv2etw5iaf3troK+jTsIqnJnXp7tEuQAuIP/19fWLGkRPS2L2jJUzVeNuy5WC+urX6YN+SDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c57ca233916f3795093bd20b34e0344a24ddce89e0989b09c414c37c2d833712","last_reissued_at":"2026-05-17T23:44:53.951446Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:53.951446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Contrastive Divergence for Combining Variational Inference and MCMC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Francisco J. R. Ruiz, Michalis K. Titsias","submitted_at":"2019-05-10T10:45:23Z","abstract_excerpt":"We develop a method to combine Markov chain Monte Carlo (MCMC) and variational inference (VI), leveraging the advantages of both inference approaches. Specifically, we improve the variational distribution by running a few MCMC steps. To make inference tractable, we introduce the variational contrastive divergence (VCD), a new divergence that replaces the standard Kullback-Leibler (KL) divergence used in VI. The VCD captures a notion of discrepancy between the initial variational distribution and its improved version (obtained after running the MCMC steps), and it converges asymptotically to th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.04062","kind":"arxiv","version":2},"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":"1905.04062","created_at":"2026-05-17T23:44:53.951592+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.04062v2","created_at":"2026-05-17T23:44:53.951592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.04062","created_at":"2026-05-17T23:44:53.951592+00:00"},{"alias_kind":"pith_short_12","alias_value":"YV6KEM4RN43Z","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"YV6KEM4RN43ZKCJ3","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"YV6KEM4R","created_at":"2026-05-18T12:33:33.725879+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/YV6KEM4RN43ZKCJ32IFTJYBUJI","json":"https://pith.science/pith/YV6KEM4RN43ZKCJ32IFTJYBUJI.json","graph_json":"https://pith.science/api/pith-number/YV6KEM4RN43ZKCJ32IFTJYBUJI/graph.json","events_json":"https://pith.science/api/pith-number/YV6KEM4RN43ZKCJ32IFTJYBUJI/events.json","paper":"https://pith.science/paper/YV6KEM4R"},"agent_actions":{"view_html":"https://pith.science/pith/YV6KEM4RN43ZKCJ32IFTJYBUJI","download_json":"https://pith.science/pith/YV6KEM4RN43ZKCJ32IFTJYBUJI.json","view_paper":"https://pith.science/paper/YV6KEM4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.04062&json=true","fetch_graph":"https://pith.science/api/pith-number/YV6KEM4RN43ZKCJ32IFTJYBUJI/graph.json","fetch_events":"https://pith.science/api/pith-number/YV6KEM4RN43ZKCJ32IFTJYBUJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YV6KEM4RN43ZKCJ32IFTJYBUJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YV6KEM4RN43ZKCJ32IFTJYBUJI/action/storage_attestation","attest_author":"https://pith.science/pith/YV6KEM4RN43ZKCJ32IFTJYBUJI/action/author_attestation","sign_citation":"https://pith.science/pith/YV6KEM4RN43ZKCJ32IFTJYBUJI/action/citation_signature","submit_replication":"https://pith.science/pith/YV6KEM4RN43ZKCJ32IFTJYBUJI/action/replication_record"}},"created_at":"2026-05-17T23:44:53.951592+00:00","updated_at":"2026-05-17T23:44:53.951592+00:00"}