{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:24SACXTGQ4EMKNQR26AU2COSJ4","short_pith_number":"pith:24SACXTG","schema_version":"1.0","canonical_sha256":"d724015e668708c53611d7814d09d24f04acfcad16b1755ba38f39d4871382fb","source":{"kind":"arxiv","id":"2602.18718","version":2},"attestation_state":"computed","paper":{"title":"Stochastic Gradient Variational Inference with Price's Gradient Estimator from Bures-Wasserstein to Parameter Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.CO"],"primary_cat":"stat.ML","authors_text":"Jacob R. Gardner, Kyurae Kim, Qiang Fu, Trevor Campbell, Yi-An Ma","submitted_at":"2026-02-21T04:52:53Z","abstract_excerpt":"For approximating a target distribution given only its unnormalized log-density, stochastic gradient-based variational inference (VI) algorithms are a popular approach. For example, Wasserstein VI (WVI) and black-box VI (BBVI) perform gradient descent in measure space (Bures-Wasserstein space) and parameter space, respectively. Previously, for the Gaussian variational family, convergence guarantees for WVI have shown superiority over existing results for black-box VI with the reparametrization gradient, suggesting the measure space approach might provide some unique benefits. In this work, how"},"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":"2602.18718","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-02-21T04:52:53Z","cross_cats_sorted":["cs.LG","math.OC","stat.CO"],"title_canon_sha256":"14ae7c85e33367272336ad7c30ba33b4399095e553dae4e1eb3794434df5d3f2","abstract_canon_sha256":"a6720a62f693bf19f8afd917312dc5c40dc16b32b7879eebd718e33f1f664158"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:06:08.858223Z","signature_b64":"5qCskZOg8UJf97abEpWu+dk1s9EfkGIfhjiHxtyCblPewu9l78feCdDa2fAJ8TxtqBHqKczayvwxb30VH2XrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d724015e668708c53611d7814d09d24f04acfcad16b1755ba38f39d4871382fb","last_reissued_at":"2026-05-20T01:06:08.857465Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:06:08.857465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Gradient Variational Inference with Price's Gradient Estimator from Bures-Wasserstein to Parameter Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.CO"],"primary_cat":"stat.ML","authors_text":"Jacob R. Gardner, Kyurae Kim, Qiang Fu, Trevor Campbell, Yi-An Ma","submitted_at":"2026-02-21T04:52:53Z","abstract_excerpt":"For approximating a target distribution given only its unnormalized log-density, stochastic gradient-based variational inference (VI) algorithms are a popular approach. For example, Wasserstein VI (WVI) and black-box VI (BBVI) perform gradient descent in measure space (Bures-Wasserstein space) and parameter space, respectively. Previously, for the Gaussian variational family, convergence guarantees for WVI have shown superiority over existing results for black-box VI with the reparametrization gradient, suggesting the measure space approach might provide some unique benefits. In this work, how"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.18718","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.18718/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":"2602.18718","created_at":"2026-05-20T01:06:08.857567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.18718v2","created_at":"2026-05-20T01:06:08.857567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.18718","created_at":"2026-05-20T01:06:08.857567+00:00"},{"alias_kind":"pith_short_12","alias_value":"24SACXTGQ4EM","created_at":"2026-05-20T01:06:08.857567+00:00"},{"alias_kind":"pith_short_16","alias_value":"24SACXTGQ4EMKNQR","created_at":"2026-05-20T01:06:08.857567+00:00"},{"alias_kind":"pith_short_8","alias_value":"24SACXTG","created_at":"2026-05-20T01:06:08.857567+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/24SACXTGQ4EMKNQR26AU2COSJ4","json":"https://pith.science/pith/24SACXTGQ4EMKNQR26AU2COSJ4.json","graph_json":"https://pith.science/api/pith-number/24SACXTGQ4EMKNQR26AU2COSJ4/graph.json","events_json":"https://pith.science/api/pith-number/24SACXTGQ4EMKNQR26AU2COSJ4/events.json","paper":"https://pith.science/paper/24SACXTG"},"agent_actions":{"view_html":"https://pith.science/pith/24SACXTGQ4EMKNQR26AU2COSJ4","download_json":"https://pith.science/pith/24SACXTGQ4EMKNQR26AU2COSJ4.json","view_paper":"https://pith.science/paper/24SACXTG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.18718&json=true","fetch_graph":"https://pith.science/api/pith-number/24SACXTGQ4EMKNQR26AU2COSJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/24SACXTGQ4EMKNQR26AU2COSJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24SACXTGQ4EMKNQR26AU2COSJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24SACXTGQ4EMKNQR26AU2COSJ4/action/storage_attestation","attest_author":"https://pith.science/pith/24SACXTGQ4EMKNQR26AU2COSJ4/action/author_attestation","sign_citation":"https://pith.science/pith/24SACXTGQ4EMKNQR26AU2COSJ4/action/citation_signature","submit_replication":"https://pith.science/pith/24SACXTGQ4EMKNQR26AU2COSJ4/action/replication_record"}},"created_at":"2026-05-20T01:06:08.857567+00:00","updated_at":"2026-05-20T01:06:08.857567+00:00"}