{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LC2XJD4OQU7U6ZOFG2YKHOG76U","short_pith_number":"pith:LC2XJD4O","schema_version":"1.0","canonical_sha256":"58b5748f8e853f4f65c536b0a3b8dff51c7c0914493bcace89ce35b7b681c48b","source":{"kind":"arxiv","id":"1708.01733","version":2},"attestation_state":"computed","paper":{"title":"Boosting Variational Inference: an Optimization Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Francesco Locatello, Gunnar R\\\"atsch, Joydeep Ghosh, Rajiv Khanna","submitted_at":"2017-08-05T08:42:11Z","abstract_excerpt":"Variational inference is a popular technique to approximate a possibly intractable Bayesian posterior with a more tractable one. Recently, boosting variational inference has been proposed as a new paradigm to approximate the posterior by a mixture of densities by greedily adding components to the mixture. However, as is the case with many other variational inference algorithms, its theoretical properties have not been studied. In the present work, we study the convergence properties of this approach from a modern optimization viewpoint by establishing connections to the classic Frank-Wolfe alg"},"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":"1708.01733","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-05T08:42:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0ad9ac43243a1b7ae5cf1031e7df9d2c95ee0c40748e9033c1bbdcea113e377d","abstract_canon_sha256":"be57c188e4f98f605b5620ad1308642b83bd46ffc393a0d3de5b2db78feafe3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:51.091168Z","signature_b64":"AzKiCkrwXDgqEoGTwwlcv9CJg7BDQaYCmGqUvzvFbzn7mw5zavXEljqfAJ/g6IXS4DXsJgVUEhz5JwrgLsslCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58b5748f8e853f4f65c536b0a3b8dff51c7c0914493bcace89ce35b7b681c48b","last_reissued_at":"2026-05-18T00:21:51.090565Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:51.090565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Variational Inference: an Optimization Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Francesco Locatello, Gunnar R\\\"atsch, Joydeep Ghosh, Rajiv Khanna","submitted_at":"2017-08-05T08:42:11Z","abstract_excerpt":"Variational inference is a popular technique to approximate a possibly intractable Bayesian posterior with a more tractable one. Recently, boosting variational inference has been proposed as a new paradigm to approximate the posterior by a mixture of densities by greedily adding components to the mixture. However, as is the case with many other variational inference algorithms, its theoretical properties have not been studied. In the present work, we study the convergence properties of this approach from a modern optimization viewpoint by establishing connections to the classic Frank-Wolfe alg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01733","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":"1708.01733","created_at":"2026-05-18T00:21:51.090655+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.01733v2","created_at":"2026-05-18T00:21:51.090655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01733","created_at":"2026-05-18T00:21:51.090655+00:00"},{"alias_kind":"pith_short_12","alias_value":"LC2XJD4OQU7U","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LC2XJD4OQU7U6ZOF","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LC2XJD4O","created_at":"2026-05-18T12:31:28.150371+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/LC2XJD4OQU7U6ZOFG2YKHOG76U","json":"https://pith.science/pith/LC2XJD4OQU7U6ZOFG2YKHOG76U.json","graph_json":"https://pith.science/api/pith-number/LC2XJD4OQU7U6ZOFG2YKHOG76U/graph.json","events_json":"https://pith.science/api/pith-number/LC2XJD4OQU7U6ZOFG2YKHOG76U/events.json","paper":"https://pith.science/paper/LC2XJD4O"},"agent_actions":{"view_html":"https://pith.science/pith/LC2XJD4OQU7U6ZOFG2YKHOG76U","download_json":"https://pith.science/pith/LC2XJD4OQU7U6ZOFG2YKHOG76U.json","view_paper":"https://pith.science/paper/LC2XJD4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.01733&json=true","fetch_graph":"https://pith.science/api/pith-number/LC2XJD4OQU7U6ZOFG2YKHOG76U/graph.json","fetch_events":"https://pith.science/api/pith-number/LC2XJD4OQU7U6ZOFG2YKHOG76U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LC2XJD4OQU7U6ZOFG2YKHOG76U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LC2XJD4OQU7U6ZOFG2YKHOG76U/action/storage_attestation","attest_author":"https://pith.science/pith/LC2XJD4OQU7U6ZOFG2YKHOG76U/action/author_attestation","sign_citation":"https://pith.science/pith/LC2XJD4OQU7U6ZOFG2YKHOG76U/action/citation_signature","submit_replication":"https://pith.science/pith/LC2XJD4OQU7U6ZOFG2YKHOG76U/action/replication_record"}},"created_at":"2026-05-18T00:21:51.090655+00:00","updated_at":"2026-05-18T00:21:51.090655+00:00"}