{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7BNR6P7HT6KPOSXLEYWJSPBW5T","short_pith_number":"pith:7BNR6P7H","schema_version":"1.0","canonical_sha256":"f85b1f3fe79f94f74aeb262c993c36ece0a32c9377dd259c98f1cfc45e04ac69","source":{"kind":"arxiv","id":"1811.02827","version":2},"attestation_state":"computed","paper":{"title":"Wasserstein variational gradient descent: From semi-discrete optimal transport to ensemble variational inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Luca Ambrogioni, Marcel van Gerven, Umut Guclu","submitted_at":"2018-11-07T10:50:40Z","abstract_excerpt":"Particle-based variational inference offers a flexible way of approximating complex posterior distributions with a set of particles. In this paper we introduce a new particle-based variational inference method based on the theory of semi-discrete optimal transport. Instead of minimizing the KL divergence between the posterior and the variational approximation, we minimize a semi-discrete optimal transport divergence. The solution of the resulting optimal transport problem provides both a particle approximation and a set of optimal transportation densities that map each particle to a segment of"},"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":"1811.02827","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-11-07T10:50:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"01f1ee12c307270eead399149de4b87a40a3604e986016465998919ba8b8f42d","abstract_canon_sha256":"17028ad134cd074f7fccd3856fbb2d6bb26ddb8c20a826cdd9fa7d3aabc60428"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:09.378952Z","signature_b64":"wuEV8C/9YfQxsybS5+u9aUAe0OysIrIl7EHn9JDrFuWHpjMhq6UvroTvS14o6K9NzhagFoWmXU8cveGhJlmYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f85b1f3fe79f94f74aeb262c993c36ece0a32c9377dd259c98f1cfc45e04ac69","last_reissued_at":"2026-05-17T23:46:09.378539Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:09.378539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wasserstein variational gradient descent: From semi-discrete optimal transport to ensemble variational inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Luca Ambrogioni, Marcel van Gerven, Umut Guclu","submitted_at":"2018-11-07T10:50:40Z","abstract_excerpt":"Particle-based variational inference offers a flexible way of approximating complex posterior distributions with a set of particles. In this paper we introduce a new particle-based variational inference method based on the theory of semi-discrete optimal transport. Instead of minimizing the KL divergence between the posterior and the variational approximation, we minimize a semi-discrete optimal transport divergence. The solution of the resulting optimal transport problem provides both a particle approximation and a set of optimal transportation densities that map each particle to a segment of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02827","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":"1811.02827","created_at":"2026-05-17T23:46:09.378608+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.02827v2","created_at":"2026-05-17T23:46:09.378608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02827","created_at":"2026-05-17T23:46:09.378608+00:00"},{"alias_kind":"pith_short_12","alias_value":"7BNR6P7HT6KP","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7BNR6P7HT6KPOSXL","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7BNR6P7H","created_at":"2026-05-18T12:32:11.075285+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/7BNR6P7HT6KPOSXLEYWJSPBW5T","json":"https://pith.science/pith/7BNR6P7HT6KPOSXLEYWJSPBW5T.json","graph_json":"https://pith.science/api/pith-number/7BNR6P7HT6KPOSXLEYWJSPBW5T/graph.json","events_json":"https://pith.science/api/pith-number/7BNR6P7HT6KPOSXLEYWJSPBW5T/events.json","paper":"https://pith.science/paper/7BNR6P7H"},"agent_actions":{"view_html":"https://pith.science/pith/7BNR6P7HT6KPOSXLEYWJSPBW5T","download_json":"https://pith.science/pith/7BNR6P7HT6KPOSXLEYWJSPBW5T.json","view_paper":"https://pith.science/paper/7BNR6P7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.02827&json=true","fetch_graph":"https://pith.science/api/pith-number/7BNR6P7HT6KPOSXLEYWJSPBW5T/graph.json","fetch_events":"https://pith.science/api/pith-number/7BNR6P7HT6KPOSXLEYWJSPBW5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7BNR6P7HT6KPOSXLEYWJSPBW5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7BNR6P7HT6KPOSXLEYWJSPBW5T/action/storage_attestation","attest_author":"https://pith.science/pith/7BNR6P7HT6KPOSXLEYWJSPBW5T/action/author_attestation","sign_citation":"https://pith.science/pith/7BNR6P7HT6KPOSXLEYWJSPBW5T/action/citation_signature","submit_replication":"https://pith.science/pith/7BNR6P7HT6KPOSXLEYWJSPBW5T/action/replication_record"}},"created_at":"2026-05-17T23:46:09.378608+00:00","updated_at":"2026-05-17T23:46:09.378608+00:00"}