{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NLLQQYPTO4ZDUQI7E2NUPGNSN2","short_pith_number":"pith:NLLQQYPT","schema_version":"1.0","canonical_sha256":"6ad70861f377323a411f269b4799b26eadd3d74bfdac85f46382f10e70032213","source":{"kind":"arxiv","id":"1810.07151","version":2},"attestation_state":"computed","paper":{"title":"Metropolis-Hastings view on variational inference and adversarial training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Dmitry Vetrov, Evgenii Egorov, Kirill Neklyudov, Pavel Shvechikov","submitted_at":"2018-10-16T17:26:24Z","abstract_excerpt":"A significant part of MCMC methods can be considered as the Metropolis-Hastings (MH) algorithm with different proposal distributions. From this point of view, the problem of constructing a sampler can be reduced to the question - how to choose a proposal for the MH algorithm? To address this question, we propose to learn an independent sampler that maximizes the acceptance rate of the MH algorithm, which, as we demonstrate, is highly related to the conventional variational inference. For Bayesian inference, the proposed method compares favorably against alternatives to sample from the posterio"},"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":"1810.07151","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-16T17:26:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d576d5c4da8506dfafdbd4de6beb011097089d513b8d90cfa27560e789a63e55","abstract_canon_sha256":"aab0520497bac0f1ba73c1739b6083449eb916edf3b40246bbdac56dd1e96475"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:50.686240Z","signature_b64":"KydGvdtKl8B/osBUzCsJ6TDszBi8iYlDwT9+sVPvh3IpqavvhobMCVYeI/R13bhylobv5SDTBSE151PbBDMJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ad70861f377323a411f269b4799b26eadd3d74bfdac85f46382f10e70032213","last_reissued_at":"2026-05-17T23:43:50.685599Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:50.685599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Metropolis-Hastings view on variational inference and adversarial training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Dmitry Vetrov, Evgenii Egorov, Kirill Neklyudov, Pavel Shvechikov","submitted_at":"2018-10-16T17:26:24Z","abstract_excerpt":"A significant part of MCMC methods can be considered as the Metropolis-Hastings (MH) algorithm with different proposal distributions. From this point of view, the problem of constructing a sampler can be reduced to the question - how to choose a proposal for the MH algorithm? To address this question, we propose to learn an independent sampler that maximizes the acceptance rate of the MH algorithm, which, as we demonstrate, is highly related to the conventional variational inference. For Bayesian inference, the proposed method compares favorably against alternatives to sample from the posterio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07151","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":"1810.07151","created_at":"2026-05-17T23:43:50.685689+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.07151v2","created_at":"2026-05-17T23:43:50.685689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07151","created_at":"2026-05-17T23:43:50.685689+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLLQQYPTO4ZD","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLLQQYPTO4ZDUQI7","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLLQQYPT","created_at":"2026-05-18T12:32:40.477152+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/NLLQQYPTO4ZDUQI7E2NUPGNSN2","json":"https://pith.science/pith/NLLQQYPTO4ZDUQI7E2NUPGNSN2.json","graph_json":"https://pith.science/api/pith-number/NLLQQYPTO4ZDUQI7E2NUPGNSN2/graph.json","events_json":"https://pith.science/api/pith-number/NLLQQYPTO4ZDUQI7E2NUPGNSN2/events.json","paper":"https://pith.science/paper/NLLQQYPT"},"agent_actions":{"view_html":"https://pith.science/pith/NLLQQYPTO4ZDUQI7E2NUPGNSN2","download_json":"https://pith.science/pith/NLLQQYPTO4ZDUQI7E2NUPGNSN2.json","view_paper":"https://pith.science/paper/NLLQQYPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.07151&json=true","fetch_graph":"https://pith.science/api/pith-number/NLLQQYPTO4ZDUQI7E2NUPGNSN2/graph.json","fetch_events":"https://pith.science/api/pith-number/NLLQQYPTO4ZDUQI7E2NUPGNSN2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLLQQYPTO4ZDUQI7E2NUPGNSN2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLLQQYPTO4ZDUQI7E2NUPGNSN2/action/storage_attestation","attest_author":"https://pith.science/pith/NLLQQYPTO4ZDUQI7E2NUPGNSN2/action/author_attestation","sign_citation":"https://pith.science/pith/NLLQQYPTO4ZDUQI7E2NUPGNSN2/action/citation_signature","submit_replication":"https://pith.science/pith/NLLQQYPTO4ZDUQI7E2NUPGNSN2/action/replication_record"}},"created_at":"2026-05-17T23:43:50.685689+00:00","updated_at":"2026-05-17T23:43:50.685689+00:00"}