{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WN6YQAJJWW7C5I4TTUWKXA546Q","short_pith_number":"pith:WN6YQAJJ","schema_version":"1.0","canonical_sha256":"b37d880129b5be2ea3939d2cab83bcf4090d259fe12b9ddac82c2dcbaa6bb31f","source":{"kind":"arxiv","id":"2310.16705","version":5},"attestation_state":"computed","paper":{"title":"Wasserstein Gradient Flow over Variational Parameter Space for Variational Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dai Hai Nguyen, Hiroshi Mamitsuka, Tetsuya Sakurai","submitted_at":"2023-10-25T15:20:53Z","abstract_excerpt":"Variational inference (VI) can be cast as an optimization problem in which the variational parameters are tuned to closely align a variational distribution with the true posterior. The optimization task can be approached through vanilla gradient descent in black-box VI or natural-gradient descent in natural-gradient VI. In this work, we reframe VI as the optimization of an objective that concerns probability distributions defined over a \\textit{variational parameter space}. Subsequently, we propose Wasserstein gradient descent for tackling this optimization problem. Notably, the optimization t"},"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":"2310.16705","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T15:20:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"14cb97fd1386bf15f8f8a14274fe3c7eb535a29a660e31f8f76e8f088991acd0","abstract_canon_sha256":"3a126d48d6c75f6662109e8d024fc3f7cf4de6bc3dd8a491c40d88c288361c43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:35.915684Z","signature_b64":"wtGI+zMlmUUIM2WfmLyCZyMuOaYgjEhB4U9JRpmTTd9mC6Lj6xNu8k8+jIqAvP2QoK/C5qc94r1QcR07jw+lDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b37d880129b5be2ea3939d2cab83bcf4090d259fe12b9ddac82c2dcbaa6bb31f","last_reissued_at":"2026-07-05T10:52:35.915168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:35.915168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wasserstein Gradient Flow over Variational Parameter Space for Variational Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dai Hai Nguyen, Hiroshi Mamitsuka, Tetsuya Sakurai","submitted_at":"2023-10-25T15:20:53Z","abstract_excerpt":"Variational inference (VI) can be cast as an optimization problem in which the variational parameters are tuned to closely align a variational distribution with the true posterior. The optimization task can be approached through vanilla gradient descent in black-box VI or natural-gradient descent in natural-gradient VI. In this work, we reframe VI as the optimization of an objective that concerns probability distributions defined over a \\textit{variational parameter space}. Subsequently, we propose Wasserstein gradient descent for tackling this optimization problem. Notably, the optimization t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16705","kind":"arxiv","version":5},"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/2310.16705/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":"2310.16705","created_at":"2026-07-05T10:52:35.915242+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.16705v5","created_at":"2026-07-05T10:52:35.915242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16705","created_at":"2026-07-05T10:52:35.915242+00:00"},{"alias_kind":"pith_short_12","alias_value":"WN6YQAJJWW7C","created_at":"2026-07-05T10:52:35.915242+00:00"},{"alias_kind":"pith_short_16","alias_value":"WN6YQAJJWW7C5I4T","created_at":"2026-07-05T10:52:35.915242+00:00"},{"alias_kind":"pith_short_8","alias_value":"WN6YQAJJ","created_at":"2026-07-05T10:52:35.915242+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18765","citing_title":"Multiple Wasserstein Gradient Descent Algorithm for Multi-Objective Distributional Optimization","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WN6YQAJJWW7C5I4TTUWKXA546Q","json":"https://pith.science/pith/WN6YQAJJWW7C5I4TTUWKXA546Q.json","graph_json":"https://pith.science/api/pith-number/WN6YQAJJWW7C5I4TTUWKXA546Q/graph.json","events_json":"https://pith.science/api/pith-number/WN6YQAJJWW7C5I4TTUWKXA546Q/events.json","paper":"https://pith.science/paper/WN6YQAJJ"},"agent_actions":{"view_html":"https://pith.science/pith/WN6YQAJJWW7C5I4TTUWKXA546Q","download_json":"https://pith.science/pith/WN6YQAJJWW7C5I4TTUWKXA546Q.json","view_paper":"https://pith.science/paper/WN6YQAJJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.16705&json=true","fetch_graph":"https://pith.science/api/pith-number/WN6YQAJJWW7C5I4TTUWKXA546Q/graph.json","fetch_events":"https://pith.science/api/pith-number/WN6YQAJJWW7C5I4TTUWKXA546Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WN6YQAJJWW7C5I4TTUWKXA546Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WN6YQAJJWW7C5I4TTUWKXA546Q/action/storage_attestation","attest_author":"https://pith.science/pith/WN6YQAJJWW7C5I4TTUWKXA546Q/action/author_attestation","sign_citation":"https://pith.science/pith/WN6YQAJJWW7C5I4TTUWKXA546Q/action/citation_signature","submit_replication":"https://pith.science/pith/WN6YQAJJWW7C5I4TTUWKXA546Q/action/replication_record"}},"created_at":"2026-07-05T10:52:35.915242+00:00","updated_at":"2026-07-05T10:52:35.915242+00:00"}