{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7ETUIMZ27PS6AOUJCI6MTA45EJ","short_pith_number":"pith:7ETUIMZ2","schema_version":"1.0","canonical_sha256":"f92744333afbe5e03a89123cc9839d225702917d58546e07de9d3021c436daf8","source":{"kind":"arxiv","id":"2101.09815","version":3},"attestation_state":"computed","paper":{"title":"Annealed Stein Variational Gradient Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Francesco D'Angelo, Vincent Fortuin","submitted_at":"2021-01-24T22:18:30Z","abstract_excerpt":"Particle based optimization algorithms have recently been developed as sampling methods that iteratively update a set of particles to approximate a target distribution. In particular Stein variational gradient descent has gained attention in the approximate inference literature for its flexibility and accuracy. We empirically explore the ability of this method to sample from multi-modal distributions and focus on two important issues: (i) the inability of the particles to escape from local modes and (ii) the inefficacy in reproducing the density of the different regions. We propose an annealin"},"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":"2101.09815","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-24T22:18:30Z","cross_cats_sorted":[],"title_canon_sha256":"17a18e26b7b840b59a903e78e09b46c1dc8348ac877c42abb23ff604222a90ac","abstract_canon_sha256":"e0b909ee9f6ceda613c5fdf871d6b09036ce1db1ef3e74af8c3c7e9741498f1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:24.897173Z","signature_b64":"dscIJH34luvzWGW47y5xucY+WcFDRz2aJScs+5lifZnVInXEjcB2ZBLQkuT1PXi3c5spbaaGwhRNOS6opBbICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f92744333afbe5e03a89123cc9839d225702917d58546e07de9d3021c436daf8","last_reissued_at":"2026-07-05T02:24:24.896789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:24.896789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Annealed Stein Variational Gradient Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Francesco D'Angelo, Vincent Fortuin","submitted_at":"2021-01-24T22:18:30Z","abstract_excerpt":"Particle based optimization algorithms have recently been developed as sampling methods that iteratively update a set of particles to approximate a target distribution. In particular Stein variational gradient descent has gained attention in the approximate inference literature for its flexibility and accuracy. We empirically explore the ability of this method to sample from multi-modal distributions and focus on two important issues: (i) the inability of the particles to escape from local modes and (ii) the inefficacy in reproducing the density of the different regions. We propose an annealin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.09815","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/2101.09815/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":"2101.09815","created_at":"2026-07-05T02:24:24.896846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.09815v3","created_at":"2026-07-05T02:24:24.896846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09815","created_at":"2026-07-05T02:24:24.896846+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ETUIMZ27PS6","created_at":"2026-07-05T02:24:24.896846+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ETUIMZ27PS6AOUJ","created_at":"2026-07-05T02:24:24.896846+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ETUIMZ2","created_at":"2026-07-05T02:24:24.896846+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/7ETUIMZ27PS6AOUJCI6MTA45EJ","json":"https://pith.science/pith/7ETUIMZ27PS6AOUJCI6MTA45EJ.json","graph_json":"https://pith.science/api/pith-number/7ETUIMZ27PS6AOUJCI6MTA45EJ/graph.json","events_json":"https://pith.science/api/pith-number/7ETUIMZ27PS6AOUJCI6MTA45EJ/events.json","paper":"https://pith.science/paper/7ETUIMZ2"},"agent_actions":{"view_html":"https://pith.science/pith/7ETUIMZ27PS6AOUJCI6MTA45EJ","download_json":"https://pith.science/pith/7ETUIMZ27PS6AOUJCI6MTA45EJ.json","view_paper":"https://pith.science/paper/7ETUIMZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.09815&json=true","fetch_graph":"https://pith.science/api/pith-number/7ETUIMZ27PS6AOUJCI6MTA45EJ/graph.json","fetch_events":"https://pith.science/api/pith-number/7ETUIMZ27PS6AOUJCI6MTA45EJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ETUIMZ27PS6AOUJCI6MTA45EJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ETUIMZ27PS6AOUJCI6MTA45EJ/action/storage_attestation","attest_author":"https://pith.science/pith/7ETUIMZ27PS6AOUJCI6MTA45EJ/action/author_attestation","sign_citation":"https://pith.science/pith/7ETUIMZ27PS6AOUJCI6MTA45EJ/action/citation_signature","submit_replication":"https://pith.science/pith/7ETUIMZ27PS6AOUJCI6MTA45EJ/action/replication_record"}},"created_at":"2026-07-05T02:24:24.896846+00:00","updated_at":"2026-07-05T02:24:24.896846+00:00"}