{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LEOUMYBCBHVW4FT74MRJXZQ5V7","short_pith_number":"pith:LEOUMYBC","schema_version":"1.0","canonical_sha256":"591d46602209eb6e167fe3229be61dafe2b886e29261a3067cbab18aeb7571aa","source":{"kind":"arxiv","id":"2106.15921","version":1},"attestation_state":"computed","paper":{"title":"Monte Carlo Variational Auto-Encoders","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Achille Thin, Alain Durmus, Arnaud Doucet, Eric Moulines, Maxim Panov, Nikita Kotelevskii","submitted_at":"2021-06-30T09:21:47Z","abstract_excerpt":"Variational auto-encoders (VAE) are popular deep latent variable models which are trained by maximizing an Evidence Lower Bound (ELBO). To obtain tighter ELBO and hence better variational approximations, it has been proposed to use importance sampling to get a lower variance estimate of the evidence. However, importance sampling is known to perform poorly in high dimensions. While it has been suggested many times in the literature to use more sophisticated algorithms such as Annealed Importance Sampling (AIS) and its Sequential Importance Sampling (SIS) extensions, the potential benefits broug"},"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":"2106.15921","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-30T09:21:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"adb8f7a8daf29ead4ccd4f8d9249d23d6b822382ac913717448ad2ded0b0fd2e","abstract_canon_sha256":"7c53e2d62c970d1d8e69e8c3f35c7dd13fa8c9917610b0b228f9570bb01e4ca5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:48.170882Z","signature_b64":"EY2Obh5oY3Ac9brPdH7BT6/x/BxrNJWrQX2dgrFLNkYezGnyb9IANZD184CNldAsfFJemMQLI+rff7Q7Gb4sDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"591d46602209eb6e167fe3229be61dafe2b886e29261a3067cbab18aeb7571aa","last_reissued_at":"2026-07-05T02:59:48.170376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:48.170376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Monte Carlo Variational Auto-Encoders","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Achille Thin, Alain Durmus, Arnaud Doucet, Eric Moulines, Maxim Panov, Nikita Kotelevskii","submitted_at":"2021-06-30T09:21:47Z","abstract_excerpt":"Variational auto-encoders (VAE) are popular deep latent variable models which are trained by maximizing an Evidence Lower Bound (ELBO). To obtain tighter ELBO and hence better variational approximations, it has been proposed to use importance sampling to get a lower variance estimate of the evidence. However, importance sampling is known to perform poorly in high dimensions. While it has been suggested many times in the literature to use more sophisticated algorithms such as Annealed Importance Sampling (AIS) and its Sequential Importance Sampling (SIS) extensions, the potential benefits broug"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15921","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/2106.15921/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":"2106.15921","created_at":"2026-07-05T02:59:48.170439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.15921v1","created_at":"2026-07-05T02:59:48.170439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15921","created_at":"2026-07-05T02:59:48.170439+00:00"},{"alias_kind":"pith_short_12","alias_value":"LEOUMYBCBHVW","created_at":"2026-07-05T02:59:48.170439+00:00"},{"alias_kind":"pith_short_16","alias_value":"LEOUMYBCBHVW4FT7","created_at":"2026-07-05T02:59:48.170439+00:00"},{"alias_kind":"pith_short_8","alias_value":"LEOUMYBC","created_at":"2026-07-05T02:59:48.170439+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/LEOUMYBCBHVW4FT74MRJXZQ5V7","json":"https://pith.science/pith/LEOUMYBCBHVW4FT74MRJXZQ5V7.json","graph_json":"https://pith.science/api/pith-number/LEOUMYBCBHVW4FT74MRJXZQ5V7/graph.json","events_json":"https://pith.science/api/pith-number/LEOUMYBCBHVW4FT74MRJXZQ5V7/events.json","paper":"https://pith.science/paper/LEOUMYBC"},"agent_actions":{"view_html":"https://pith.science/pith/LEOUMYBCBHVW4FT74MRJXZQ5V7","download_json":"https://pith.science/pith/LEOUMYBCBHVW4FT74MRJXZQ5V7.json","view_paper":"https://pith.science/paper/LEOUMYBC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.15921&json=true","fetch_graph":"https://pith.science/api/pith-number/LEOUMYBCBHVW4FT74MRJXZQ5V7/graph.json","fetch_events":"https://pith.science/api/pith-number/LEOUMYBCBHVW4FT74MRJXZQ5V7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LEOUMYBCBHVW4FT74MRJXZQ5V7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LEOUMYBCBHVW4FT74MRJXZQ5V7/action/storage_attestation","attest_author":"https://pith.science/pith/LEOUMYBCBHVW4FT74MRJXZQ5V7/action/author_attestation","sign_citation":"https://pith.science/pith/LEOUMYBCBHVW4FT74MRJXZQ5V7/action/citation_signature","submit_replication":"https://pith.science/pith/LEOUMYBCBHVW4FT74MRJXZQ5V7/action/replication_record"}},"created_at":"2026-07-05T02:59:48.170439+00:00","updated_at":"2026-07-05T02:59:48.170439+00:00"}