{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XMNKW2WWZ56FUMR37FPIV2FYGH","short_pith_number":"pith:XMNKW2WW","schema_version":"1.0","canonical_sha256":"bb1aab6ad6cf7c5a323bf95e8ae8b831f05a3d635d68b4af2da2a221b2efcf6c","source":{"kind":"arxiv","id":"1802.10174","version":5},"attestation_state":"computed","paper":{"title":"Mirrored Langevin Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Ali Kavis, Paul Rolland, Volkan Cevher, Ya-Ping Hsieh","submitted_at":"2018-02-27T21:31:53Z","abstract_excerpt":"We consider the problem of sampling from constrained distributions, which has posed significant challenges to both non-asymptotic analysis and algorithmic design. We propose a unified framework, which is inspired by the classical mirror descent, to derive novel first-order sampling schemes. We prove that, for a general target distribution with strongly convex potential, our framework implies the existence of a first-order algorithm achieving $\\tilde{O}(\\epsilon^{-2}d)$ convergence, suggesting that the state-of-the-art $\\tilde{O}(\\epsilon^{-6}d^5)$ can be vastly improved. With the important Lat"},"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":"1802.10174","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-27T21:31:53Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"8f28c0f986d2cf76e97159cca098ac58848b0d1f8d238e28e80788f9f315ed8d","abstract_canon_sha256":"9540691954c9073eba8c0fcba2e359183cf4b57103cae5a87bb5f23e3f4aff74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:02:49.325042Z","signature_b64":"7ZqltR5ZAYWdXx9VsEEDdPL9P0ZFxWkwkqaoS98yPJ2s+mEn1bF6Vgui6qovPE2kbKZnjTFqVCWRPbqN+S7cBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb1aab6ad6cf7c5a323bf95e8ae8b831f05a3d635d68b4af2da2a221b2efcf6c","last_reissued_at":"2026-07-05T02:02:49.324583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:02:49.324583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mirrored Langevin Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Ali Kavis, Paul Rolland, Volkan Cevher, Ya-Ping Hsieh","submitted_at":"2018-02-27T21:31:53Z","abstract_excerpt":"We consider the problem of sampling from constrained distributions, which has posed significant challenges to both non-asymptotic analysis and algorithmic design. We propose a unified framework, which is inspired by the classical mirror descent, to derive novel first-order sampling schemes. We prove that, for a general target distribution with strongly convex potential, our framework implies the existence of a first-order algorithm achieving $\\tilde{O}(\\epsilon^{-2}d)$ convergence, suggesting that the state-of-the-art $\\tilde{O}(\\epsilon^{-6}d^5)$ can be vastly improved. With the important Lat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10174","kind":"arxiv","version":5},"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/1802.10174/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":"1802.10174","created_at":"2026-07-05T02:02:49.324644+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.10174v5","created_at":"2026-07-05T02:02:49.324644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10174","created_at":"2026-07-05T02:02:49.324644+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMNKW2WWZ56F","created_at":"2026-07-05T02:02:49.324644+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMNKW2WWZ56FUMR3","created_at":"2026-07-05T02:02:49.324644+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMNKW2WW","created_at":"2026-07-05T02:02:49.324644+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02415","citing_title":"Generative models on phase space","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMNKW2WWZ56FUMR37FPIV2FYGH","json":"https://pith.science/pith/XMNKW2WWZ56FUMR37FPIV2FYGH.json","graph_json":"https://pith.science/api/pith-number/XMNKW2WWZ56FUMR37FPIV2FYGH/graph.json","events_json":"https://pith.science/api/pith-number/XMNKW2WWZ56FUMR37FPIV2FYGH/events.json","paper":"https://pith.science/paper/XMNKW2WW"},"agent_actions":{"view_html":"https://pith.science/pith/XMNKW2WWZ56FUMR37FPIV2FYGH","download_json":"https://pith.science/pith/XMNKW2WWZ56FUMR37FPIV2FYGH.json","view_paper":"https://pith.science/paper/XMNKW2WW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.10174&json=true","fetch_graph":"https://pith.science/api/pith-number/XMNKW2WWZ56FUMR37FPIV2FYGH/graph.json","fetch_events":"https://pith.science/api/pith-number/XMNKW2WWZ56FUMR37FPIV2FYGH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMNKW2WWZ56FUMR37FPIV2FYGH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMNKW2WWZ56FUMR37FPIV2FYGH/action/storage_attestation","attest_author":"https://pith.science/pith/XMNKW2WWZ56FUMR37FPIV2FYGH/action/author_attestation","sign_citation":"https://pith.science/pith/XMNKW2WWZ56FUMR37FPIV2FYGH/action/citation_signature","submit_replication":"https://pith.science/pith/XMNKW2WWZ56FUMR37FPIV2FYGH/action/replication_record"}},"created_at":"2026-07-05T02:02:49.324644+00:00","updated_at":"2026-07-05T02:02:49.324644+00:00"}