{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SCGPXCZODKO324DEIH7RKWHFZK","short_pith_number":"pith:SCGPXCZO","schema_version":"1.0","canonical_sha256":"908cfb8b2e1a9dbd706441ff1558e5ca93ea0dbebf79b739c75efa72da95e85f","source":{"kind":"arxiv","id":"2210.00462","version":3},"attestation_state":"computed","paper":{"title":"Improved Stein Variational Gradient Descent with Importance Weights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Lukang Sun, Peter Richt\\'arik","submitted_at":"2022-10-02T08:42:44Z","abstract_excerpt":"Stein Variational Gradient Descent (SVGD) is a popular sampling algorithm used in various machine learning tasks. It is well known that SVGD arises from a discretization of the kernelized gradient flow of the Kullback-Leibler divergence $D_{KL}\\left(\\cdot\\mid\\pi\\right)$, where $\\pi$ is the target distribution. In this work, we propose to enhance SVGD via the introduction of importance weights, which leads to a new method for which we coin the name $\\beta$-SVGD. In the continuous time and infinite particles regime, the time for this flow to converge to the equilibrium distribution $\\pi$, quanti"},"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":"2210.00462","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-02T08:42:44Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"1b30a3ae22404b4432873c064b49ca5986739f45517453b42fed5888bca61d3e","abstract_canon_sha256":"fdb39da9468b943152302ab65a0b9c6e1abb744fc9cef9d0bbb6207bd4ff5e8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:47.813111Z","signature_b64":"7ypzhYxOvxZ3tnRHrnPgO3R8W5cFvvOIL7hsIGQqh18eKJr/Th+5SfcsCYHxw5O5ZPUAfut1LwK5DkEPsHpCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"908cfb8b2e1a9dbd706441ff1558e5ca93ea0dbebf79b739c75efa72da95e85f","last_reissued_at":"2026-07-05T05:17:47.812749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:47.812749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Stein Variational Gradient Descent with Importance Weights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Lukang Sun, Peter Richt\\'arik","submitted_at":"2022-10-02T08:42:44Z","abstract_excerpt":"Stein Variational Gradient Descent (SVGD) is a popular sampling algorithm used in various machine learning tasks. It is well known that SVGD arises from a discretization of the kernelized gradient flow of the Kullback-Leibler divergence $D_{KL}\\left(\\cdot\\mid\\pi\\right)$, where $\\pi$ is the target distribution. In this work, we propose to enhance SVGD via the introduction of importance weights, which leads to a new method for which we coin the name $\\beta$-SVGD. In the continuous time and infinite particles regime, the time for this flow to converge to the equilibrium distribution $\\pi$, quanti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00462","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/2210.00462/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":"2210.00462","created_at":"2026-07-05T05:17:47.812821+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00462v3","created_at":"2026-07-05T05:17:47.812821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00462","created_at":"2026-07-05T05:17:47.812821+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCGPXCZODKO3","created_at":"2026-07-05T05:17:47.812821+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCGPXCZODKO324DE","created_at":"2026-07-05T05:17:47.812821+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCGPXCZO","created_at":"2026-07-05T05:17:47.812821+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/SCGPXCZODKO324DEIH7RKWHFZK","json":"https://pith.science/pith/SCGPXCZODKO324DEIH7RKWHFZK.json","graph_json":"https://pith.science/api/pith-number/SCGPXCZODKO324DEIH7RKWHFZK/graph.json","events_json":"https://pith.science/api/pith-number/SCGPXCZODKO324DEIH7RKWHFZK/events.json","paper":"https://pith.science/paper/SCGPXCZO"},"agent_actions":{"view_html":"https://pith.science/pith/SCGPXCZODKO324DEIH7RKWHFZK","download_json":"https://pith.science/pith/SCGPXCZODKO324DEIH7RKWHFZK.json","view_paper":"https://pith.science/paper/SCGPXCZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00462&json=true","fetch_graph":"https://pith.science/api/pith-number/SCGPXCZODKO324DEIH7RKWHFZK/graph.json","fetch_events":"https://pith.science/api/pith-number/SCGPXCZODKO324DEIH7RKWHFZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCGPXCZODKO324DEIH7RKWHFZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCGPXCZODKO324DEIH7RKWHFZK/action/storage_attestation","attest_author":"https://pith.science/pith/SCGPXCZODKO324DEIH7RKWHFZK/action/author_attestation","sign_citation":"https://pith.science/pith/SCGPXCZODKO324DEIH7RKWHFZK/action/citation_signature","submit_replication":"https://pith.science/pith/SCGPXCZODKO324DEIH7RKWHFZK/action/replication_record"}},"created_at":"2026-07-05T05:17:47.812821+00:00","updated_at":"2026-07-05T05:17:47.812821+00:00"}