{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6LRRXTJVYPX6VCLOTZHCW5TQJS","short_pith_number":"pith:6LRRXTJV","schema_version":"1.0","canonical_sha256":"f2e31bcd35c3efea896e9e4e2b76704cbb124692dda58b15b7f1eda0ea7e7e93","source":{"kind":"arxiv","id":"2106.12506","version":3},"attestation_state":"computed","paper":{"title":"Sampling with Mirrored Stein Operators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chang Liu, Jiaxin Shi, Lester Mackey","submitted_at":"2021-06-23T16:23:34Z","abstract_excerpt":"We introduce a new family of particle evolution samplers suitable for constrained domains and non-Euclidean geometries. Stein Variational Mirror Descent and Mirrored Stein Variational Gradient Descent minimize the Kullback-Leibler (KL) divergence to constrained target distributions by evolving particles in a dual space defined by a mirror map. Stein Variational Natural Gradient exploits non-Euclidean geometry to more efficiently minimize the KL divergence to unconstrained targets. We derive these samplers from a new class of mirrored Stein operators and adaptive kernels developed in this work."},"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":"2106.12506","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-23T16:23:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"140786c6b28dc7061fe0c1ac3ec0d533c5aea5fc43d0fafffac27bbce378d7c3","abstract_canon_sha256":"2b14bf8baef977b2564bcd3746c87287e9f7bf3e774c3ad01f3be1e6e719a74d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:15.119268Z","signature_b64":"SkoMBG3CYs2I5kifeTRJF06SFVJD8Igb9qBcqSHDrK7c8GfzXk31YDsWeF0F6O+OwDUVrsjIy46MzRvrZtypCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2e31bcd35c3efea896e9e4e2b76704cbb124692dda58b15b7f1eda0ea7e7e93","last_reissued_at":"2026-07-05T04:17:15.118731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:15.118731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sampling with Mirrored Stein Operators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chang Liu, Jiaxin Shi, Lester Mackey","submitted_at":"2021-06-23T16:23:34Z","abstract_excerpt":"We introduce a new family of particle evolution samplers suitable for constrained domains and non-Euclidean geometries. Stein Variational Mirror Descent and Mirrored Stein Variational Gradient Descent minimize the Kullback-Leibler (KL) divergence to constrained target distributions by evolving particles in a dual space defined by a mirror map. Stein Variational Natural Gradient exploits non-Euclidean geometry to more efficiently minimize the KL divergence to unconstrained targets. We derive these samplers from a new class of mirrored Stein operators and adaptive kernels developed in this work."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.12506","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/2106.12506/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":"2106.12506","created_at":"2026-07-05T04:17:15.118783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.12506v3","created_at":"2026-07-05T04:17:15.118783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.12506","created_at":"2026-07-05T04:17:15.118783+00:00"},{"alias_kind":"pith_short_12","alias_value":"6LRRXTJVYPX6","created_at":"2026-07-05T04:17:15.118783+00:00"},{"alias_kind":"pith_short_16","alias_value":"6LRRXTJVYPX6VCLO","created_at":"2026-07-05T04:17:15.118783+00:00"},{"alias_kind":"pith_short_8","alias_value":"6LRRXTJV","created_at":"2026-07-05T04:17:15.118783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01942","citing_title":"Efficient Bayesian Sampling with Langevin Birth-Death Dynamics","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6LRRXTJVYPX6VCLOTZHCW5TQJS","json":"https://pith.science/pith/6LRRXTJVYPX6VCLOTZHCW5TQJS.json","graph_json":"https://pith.science/api/pith-number/6LRRXTJVYPX6VCLOTZHCW5TQJS/graph.json","events_json":"https://pith.science/api/pith-number/6LRRXTJVYPX6VCLOTZHCW5TQJS/events.json","paper":"https://pith.science/paper/6LRRXTJV"},"agent_actions":{"view_html":"https://pith.science/pith/6LRRXTJVYPX6VCLOTZHCW5TQJS","download_json":"https://pith.science/pith/6LRRXTJVYPX6VCLOTZHCW5TQJS.json","view_paper":"https://pith.science/paper/6LRRXTJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.12506&json=true","fetch_graph":"https://pith.science/api/pith-number/6LRRXTJVYPX6VCLOTZHCW5TQJS/graph.json","fetch_events":"https://pith.science/api/pith-number/6LRRXTJVYPX6VCLOTZHCW5TQJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6LRRXTJVYPX6VCLOTZHCW5TQJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6LRRXTJVYPX6VCLOTZHCW5TQJS/action/storage_attestation","attest_author":"https://pith.science/pith/6LRRXTJVYPX6VCLOTZHCW5TQJS/action/author_attestation","sign_citation":"https://pith.science/pith/6LRRXTJVYPX6VCLOTZHCW5TQJS/action/citation_signature","submit_replication":"https://pith.science/pith/6LRRXTJVYPX6VCLOTZHCW5TQJS/action/replication_record"}},"created_at":"2026-07-05T04:17:15.118783+00:00","updated_at":"2026-07-05T04:17:15.118783+00:00"}