{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GZQZKZSA4C4DYO4GCD5A676CUK","short_pith_number":"pith:GZQZKZSA","schema_version":"1.0","canonical_sha256":"3661956640e0b83c3b8610fa0f7fc2a29a3e4d337a032d0416d042231bb20e77","source":{"kind":"arxiv","id":"2409.08469","version":3},"attestation_state":"computed","paper":{"title":"Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Krishnakumar Balasubramanian, Promit Ghosal, Sayan Banerjee","submitted_at":"2024-09-13T01:49:19Z","abstract_excerpt":"We provide finite-particle convergence rates for the Stein Variational Gradient Descent (SVGD) algorithm in the Kernelized Stein Discrepancy ($\\mathsf{KSD}$) and Wasserstein-2 metrics. Our key insight is that the time derivative of the relative entropy between the joint density of $N$ particle locations and the $N$-fold product target measure, starting from a regular initial distribution, splits into a dominant `negative part' proportional to $N$ times the expected $\\mathsf{KSD}^2$ and a smaller `positive part'. This observation leads to $\\mathsf{KSD}$ rates of order $1/\\sqrt{N}$, in both cont"},"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":"2409.08469","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2024-09-13T01:49:19Z","cross_cats_sorted":["cs.LG","math.PR","stat.ML","stat.TH"],"title_canon_sha256":"bed44c669935d540639a40a19aa6863c5c007726535f0dedd106bcf1b7e2bafe","abstract_canon_sha256":"4810d0d913f1504ce6664763293087f75fc6dba0ff348724fe90a3dff190db00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:35.768189Z","signature_b64":"b8/uuZAnRTdUyDkv9IPikkxj46NwvceE/78u8yHmh7mv5IOlw3CKpF6+TNtDLafsnKP3/N3bM+PfkO1aYFD6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3661956640e0b83c3b8610fa0f7fc2a29a3e4d337a032d0416d042231bb20e77","last_reissued_at":"2026-07-05T11:17:35.767692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:35.767692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Krishnakumar Balasubramanian, Promit Ghosal, Sayan Banerjee","submitted_at":"2024-09-13T01:49:19Z","abstract_excerpt":"We provide finite-particle convergence rates for the Stein Variational Gradient Descent (SVGD) algorithm in the Kernelized Stein Discrepancy ($\\mathsf{KSD}$) and Wasserstein-2 metrics. Our key insight is that the time derivative of the relative entropy between the joint density of $N$ particle locations and the $N$-fold product target measure, starting from a regular initial distribution, splits into a dominant `negative part' proportional to $N$ times the expected $\\mathsf{KSD}^2$ and a smaller `positive part'. This observation leads to $\\mathsf{KSD}$ rates of order $1/\\sqrt{N}$, in both cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08469","kind":"arxiv","version":3},"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/2409.08469/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":"2409.08469","created_at":"2026-07-05T11:17:35.767749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08469v3","created_at":"2026-07-05T11:17:35.767749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08469","created_at":"2026-07-05T11:17:35.767749+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZQZKZSA4C4D","created_at":"2026-07-05T11:17:35.767749+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZQZKZSA4C4DYO4G","created_at":"2026-07-05T11:17:35.767749+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZQZKZSA","created_at":"2026-07-05T11:17:35.767749+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":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZQZKZSA4C4DYO4GCD5A676CUK","json":"https://pith.science/pith/GZQZKZSA4C4DYO4GCD5A676CUK.json","graph_json":"https://pith.science/api/pith-number/GZQZKZSA4C4DYO4GCD5A676CUK/graph.json","events_json":"https://pith.science/api/pith-number/GZQZKZSA4C4DYO4GCD5A676CUK/events.json","paper":"https://pith.science/paper/GZQZKZSA"},"agent_actions":{"view_html":"https://pith.science/pith/GZQZKZSA4C4DYO4GCD5A676CUK","download_json":"https://pith.science/pith/GZQZKZSA4C4DYO4GCD5A676CUK.json","view_paper":"https://pith.science/paper/GZQZKZSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08469&json=true","fetch_graph":"https://pith.science/api/pith-number/GZQZKZSA4C4DYO4GCD5A676CUK/graph.json","fetch_events":"https://pith.science/api/pith-number/GZQZKZSA4C4DYO4GCD5A676CUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZQZKZSA4C4DYO4GCD5A676CUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZQZKZSA4C4DYO4GCD5A676CUK/action/storage_attestation","attest_author":"https://pith.science/pith/GZQZKZSA4C4DYO4GCD5A676CUK/action/author_attestation","sign_citation":"https://pith.science/pith/GZQZKZSA4C4DYO4GCD5A676CUK/action/citation_signature","submit_replication":"https://pith.science/pith/GZQZKZSA4C4DYO4GCD5A676CUK/action/replication_record"}},"created_at":"2026-07-05T11:17:35.767749+00:00","updated_at":"2026-07-05T11:17:35.767749+00:00"}