{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FG3EOUZWFE2P43YWUKN3F3LZKZ","short_pith_number":"pith:FG3EOUZW","schema_version":"1.0","canonical_sha256":"29b64753362934fe6f16a29bb2ed79567a067560f5136eb341d647e03fca37bc","source":{"kind":"arxiv","id":"1711.10927","version":1},"attestation_state":"computed","paper":{"title":"Particle Optimization in Stochastic Gradient MCMC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Changyou Chen, Ruiyi Zhang","submitted_at":"2017-11-29T15:54:29Z","abstract_excerpt":"Stochastic gradient Markov chain Monte Carlo (SG-MCMC) has been increasingly popular in Bayesian learning due to its ability to deal with large data. A standard SG-MCMC algorithm simulates samples from a discretized-time Markov chain to approximate a target distribution. However, the samples are typically highly correlated due to the sequential generation process, an undesired property in SG-MCMC. In contrary, Stein variational gradient descent (SVGD) directly optimizes a set of particles, and it is able to approximate a target distribution with much fewer samples. In this paper, we propose a "},"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":"1711.10927","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-29T15:54:29Z","cross_cats_sorted":[],"title_canon_sha256":"8fe7eefd7a73291824a4a302d55aa195ebada702147c9374bcee527964cf0bd2","abstract_canon_sha256":"97d8fbf0399a9b811da9b1ec48684912ed340cea921730f072a6db9ba02dff82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:16.433489Z","signature_b64":"Q0yLbvdoPgKGhPe3g2lJP2+/tniUEAIFXVjiPlq+XdcrasZT/QfiHwU5sdLu6XMFW5tG/uwEooCSpkUD9IidBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29b64753362934fe6f16a29bb2ed79567a067560f5136eb341d647e03fca37bc","last_reissued_at":"2026-05-18T00:29:16.432874Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:16.432874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Particle Optimization in Stochastic Gradient MCMC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Changyou Chen, Ruiyi Zhang","submitted_at":"2017-11-29T15:54:29Z","abstract_excerpt":"Stochastic gradient Markov chain Monte Carlo (SG-MCMC) has been increasingly popular in Bayesian learning due to its ability to deal with large data. A standard SG-MCMC algorithm simulates samples from a discretized-time Markov chain to approximate a target distribution. However, the samples are typically highly correlated due to the sequential generation process, an undesired property in SG-MCMC. In contrary, Stein variational gradient descent (SVGD) directly optimizes a set of particles, and it is able to approximate a target distribution with much fewer samples. In this paper, we propose a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.10927","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1711.10927","created_at":"2026-05-18T00:29:16.432964+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.10927v1","created_at":"2026-05-18T00:29:16.432964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.10927","created_at":"2026-05-18T00:29:16.432964+00:00"},{"alias_kind":"pith_short_12","alias_value":"FG3EOUZWFE2P","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FG3EOUZWFE2P43YW","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FG3EOUZW","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18765","citing_title":"Multiple Wasserstein Gradient Descent Algorithm for Multi-Objective Distributional Optimization","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FG3EOUZWFE2P43YWUKN3F3LZKZ","json":"https://pith.science/pith/FG3EOUZWFE2P43YWUKN3F3LZKZ.json","graph_json":"https://pith.science/api/pith-number/FG3EOUZWFE2P43YWUKN3F3LZKZ/graph.json","events_json":"https://pith.science/api/pith-number/FG3EOUZWFE2P43YWUKN3F3LZKZ/events.json","paper":"https://pith.science/paper/FG3EOUZW"},"agent_actions":{"view_html":"https://pith.science/pith/FG3EOUZWFE2P43YWUKN3F3LZKZ","download_json":"https://pith.science/pith/FG3EOUZWFE2P43YWUKN3F3LZKZ.json","view_paper":"https://pith.science/paper/FG3EOUZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.10927&json=true","fetch_graph":"https://pith.science/api/pith-number/FG3EOUZWFE2P43YWUKN3F3LZKZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FG3EOUZWFE2P43YWUKN3F3LZKZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FG3EOUZWFE2P43YWUKN3F3LZKZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FG3EOUZWFE2P43YWUKN3F3LZKZ/action/storage_attestation","attest_author":"https://pith.science/pith/FG3EOUZWFE2P43YWUKN3F3LZKZ/action/author_attestation","sign_citation":"https://pith.science/pith/FG3EOUZWFE2P43YWUKN3F3LZKZ/action/citation_signature","submit_replication":"https://pith.science/pith/FG3EOUZWFE2P43YWUKN3F3LZKZ/action/replication_record"}},"created_at":"2026-05-18T00:29:16.432964+00:00","updated_at":"2026-05-18T00:29:16.432964+00:00"}