{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:KIWYS2F4HWRTAZCNAIVZK6V76O","short_pith_number":"pith:KIWYS2F4","schema_version":"1.0","canonical_sha256":"522d8968bc3da330644d022b957abff380f684880f8ebdedff3cd2ccb29c4390","source":{"kind":"arxiv","id":"1611.00328","version":4},"attestation_state":"computed","paper":{"title":"Variational Inference via $\\chi$-Upper Bound Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.CO","stat.ME"],"primary_cat":"stat.ML","authors_text":"Adji B. Dieng, David M. Blei, Dustin Tran, John Paisley, Rajesh Ranganath","submitted_at":"2016-11-01T18:40:23Z","abstract_excerpt":"Variational inference (VI) is widely used as an efficient alternative to Markov chain Monte Carlo. It posits a family of approximating distributions $q$ and finds the closest member to the exact posterior $p$. Closeness is usually measured via a divergence $D(q || p)$ from $q$ to $p$. While successful, this approach also has problems. Notably, it typically leads to underestimation of the posterior variance. In this paper we propose CHIVI, a black-box variational inference algorithm that minimizes $D_{\\chi}(p || q)$, the $\\chi$-divergence from $p$ to $q$. CHIVI minimizes an upper bound of the m"},"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":"1611.00328","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-01T18:40:23Z","cross_cats_sorted":["cs.LG","stat.CO","stat.ME"],"title_canon_sha256":"e5ac4d75e01d67c451f18681adb819cfccb188e4ce044b90cb01b76f110a4fb2","abstract_canon_sha256":"78e9b00e46132c7a5a22c783f7f4800892b4f5ea59d05157e363184402ee747a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:46.669397Z","signature_b64":"q7HMVJPFM+dOv2Nf7Tbt1rQkkb8BAEyCl8cqiMGMVswfFjYBDSoxd732HOGQyarB6+4uh3WbBK0dFeR3/HESDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"522d8968bc3da330644d022b957abff380f684880f8ebdedff3cd2ccb29c4390","last_reissued_at":"2026-05-18T00:30:46.668670Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:46.668670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Inference via $\\chi$-Upper Bound Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.CO","stat.ME"],"primary_cat":"stat.ML","authors_text":"Adji B. Dieng, David M. Blei, Dustin Tran, John Paisley, Rajesh Ranganath","submitted_at":"2016-11-01T18:40:23Z","abstract_excerpt":"Variational inference (VI) is widely used as an efficient alternative to Markov chain Monte Carlo. It posits a family of approximating distributions $q$ and finds the closest member to the exact posterior $p$. Closeness is usually measured via a divergence $D(q || p)$ from $q$ to $p$. While successful, this approach also has problems. Notably, it typically leads to underestimation of the posterior variance. In this paper we propose CHIVI, a black-box variational inference algorithm that minimizes $D_{\\chi}(p || q)$, the $\\chi$-divergence from $p$ to $q$. CHIVI minimizes an upper bound of the m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.00328","kind":"arxiv","version":4},"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":"1611.00328","created_at":"2026-05-18T00:30:46.668785+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.00328v4","created_at":"2026-05-18T00:30:46.668785+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.00328","created_at":"2026-05-18T00:30:46.668785+00:00"},{"alias_kind":"pith_short_12","alias_value":"KIWYS2F4HWRT","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"KIWYS2F4HWRTAZCN","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"KIWYS2F4","created_at":"2026-05-18T12:30:25.849896+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/KIWYS2F4HWRTAZCNAIVZK6V76O","json":"https://pith.science/pith/KIWYS2F4HWRTAZCNAIVZK6V76O.json","graph_json":"https://pith.science/api/pith-number/KIWYS2F4HWRTAZCNAIVZK6V76O/graph.json","events_json":"https://pith.science/api/pith-number/KIWYS2F4HWRTAZCNAIVZK6V76O/events.json","paper":"https://pith.science/paper/KIWYS2F4"},"agent_actions":{"view_html":"https://pith.science/pith/KIWYS2F4HWRTAZCNAIVZK6V76O","download_json":"https://pith.science/pith/KIWYS2F4HWRTAZCNAIVZK6V76O.json","view_paper":"https://pith.science/paper/KIWYS2F4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.00328&json=true","fetch_graph":"https://pith.science/api/pith-number/KIWYS2F4HWRTAZCNAIVZK6V76O/graph.json","fetch_events":"https://pith.science/api/pith-number/KIWYS2F4HWRTAZCNAIVZK6V76O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KIWYS2F4HWRTAZCNAIVZK6V76O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KIWYS2F4HWRTAZCNAIVZK6V76O/action/storage_attestation","attest_author":"https://pith.science/pith/KIWYS2F4HWRTAZCNAIVZK6V76O/action/author_attestation","sign_citation":"https://pith.science/pith/KIWYS2F4HWRTAZCNAIVZK6V76O/action/citation_signature","submit_replication":"https://pith.science/pith/KIWYS2F4HWRTAZCNAIVZK6V76O/action/replication_record"}},"created_at":"2026-05-18T00:30:46.668785+00:00","updated_at":"2026-05-18T00:30:46.668785+00:00"}