{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QCRWJKGG3HT2RZWSUIAOFCP4ER","short_pith_number":"pith:QCRWJKGG","schema_version":"1.0","canonical_sha256":"80a364a8c6d9e7a8e6d2a200e289fc2446730a38e3601e76f0e5b69bde37df85","source":{"kind":"arxiv","id":"2602.05172","version":2},"attestation_state":"computed","paper":{"title":"Finite-Particle Rates for Regularized Stein Variational Gradient Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Krishnakumar Balasubramanian, Promit Ghosal, Sayan Banerjee, Ye He","submitted_at":"2026-02-05T01:00:00Z","abstract_excerpt":"We derive finite-particle rates for the regularized Stein variational gradient descent (R-SVGD) algorithm introduced by He et al. (2024) that corrects the constant-order bias of the SVGD by applying a resolvent-type preconditioner to the kernelized Wasserstein gradient. For the resulting interacting $N$-particle system, we establish explicit non-asymptotic bounds for time-averaged (annealed) empirical measures, illustrating convergence in the \\emph{true} (non-kernelized) Fisher information and, under a $\\mathrm{W}_1\\mathrm{I}$ condition on the target, corresponding $\\mathrm{W}_1$ convergence f"},"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":"2602.05172","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-02-05T01:00:00Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"2073ac06833f64160aac0f1a62082889e5aa290d7858cf5c19095750030f049f","abstract_canon_sha256":"02ba567166390c0f02ba010e40e1719fc90348c0b0f2be7ae086b7f4311dc478"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:41.701179Z","signature_b64":"YYq+tEnO/WkxsFYoqZA/GI4hJvHRJM86ERgBG/s6RRnvC5SPjukraqjJ1PWfxWxENHnb3CipJOUYzVvHpJOYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80a364a8c6d9e7a8e6d2a200e289fc2446730a38e3601e76f0e5b69bde37df85","last_reissued_at":"2026-05-20T00:05:41.700536Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:41.700536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finite-Particle Rates for Regularized Stein Variational Gradient Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Krishnakumar Balasubramanian, Promit Ghosal, Sayan Banerjee, Ye He","submitted_at":"2026-02-05T01:00:00Z","abstract_excerpt":"We derive finite-particle rates for the regularized Stein variational gradient descent (R-SVGD) algorithm introduced by He et al. (2024) that corrects the constant-order bias of the SVGD by applying a resolvent-type preconditioner to the kernelized Wasserstein gradient. For the resulting interacting $N$-particle system, we establish explicit non-asymptotic bounds for time-averaged (annealed) empirical measures, illustrating convergence in the \\emph{true} (non-kernelized) Fisher information and, under a $\\mathrm{W}_1\\mathrm{I}$ condition on the target, corresponding $\\mathrm{W}_1$ convergence f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.05172","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/2602.05172/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":"2602.05172","created_at":"2026-05-20T00:05:41.700635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.05172v2","created_at":"2026-05-20T00:05:41.700635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.05172","created_at":"2026-05-20T00:05:41.700635+00:00"},{"alias_kind":"pith_short_12","alias_value":"QCRWJKGG3HT2","created_at":"2026-05-20T00:05:41.700635+00:00"},{"alias_kind":"pith_short_16","alias_value":"QCRWJKGG3HT2RZWS","created_at":"2026-05-20T00:05:41.700635+00:00"},{"alias_kind":"pith_short_8","alias_value":"QCRWJKGG","created_at":"2026-05-20T00:05:41.700635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.03627","citing_title":"Stein Variational Gradient Descent dynamics for highly concentrated kernels","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QCRWJKGG3HT2RZWSUIAOFCP4ER","json":"https://pith.science/pith/QCRWJKGG3HT2RZWSUIAOFCP4ER.json","graph_json":"https://pith.science/api/pith-number/QCRWJKGG3HT2RZWSUIAOFCP4ER/graph.json","events_json":"https://pith.science/api/pith-number/QCRWJKGG3HT2RZWSUIAOFCP4ER/events.json","paper":"https://pith.science/paper/QCRWJKGG"},"agent_actions":{"view_html":"https://pith.science/pith/QCRWJKGG3HT2RZWSUIAOFCP4ER","download_json":"https://pith.science/pith/QCRWJKGG3HT2RZWSUIAOFCP4ER.json","view_paper":"https://pith.science/paper/QCRWJKGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.05172&json=true","fetch_graph":"https://pith.science/api/pith-number/QCRWJKGG3HT2RZWSUIAOFCP4ER/graph.json","fetch_events":"https://pith.science/api/pith-number/QCRWJKGG3HT2RZWSUIAOFCP4ER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QCRWJKGG3HT2RZWSUIAOFCP4ER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QCRWJKGG3HT2RZWSUIAOFCP4ER/action/storage_attestation","attest_author":"https://pith.science/pith/QCRWJKGG3HT2RZWSUIAOFCP4ER/action/author_attestation","sign_citation":"https://pith.science/pith/QCRWJKGG3HT2RZWSUIAOFCP4ER/action/citation_signature","submit_replication":"https://pith.science/pith/QCRWJKGG3HT2RZWSUIAOFCP4ER/action/replication_record"}},"created_at":"2026-05-20T00:05:41.700635+00:00","updated_at":"2026-05-20T00:05:41.700635+00:00"}