{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:L4YSL2ML6QF6B47HPVD6OOECF6","short_pith_number":"pith:L4YSL2ML","schema_version":"1.0","canonical_sha256":"5f3125e98bf40be0f3e77d47e738822fa4a1b6cac51389f1014861925d99dea1","source":{"kind":"arxiv","id":"2203.10215","version":3},"attestation_state":"computed","paper":{"title":"Convergence Error Analysis of Reflected Gradient Langevin Dynamics for Globally Optimizing Non-Convex Constrained Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.PR","stat.ML"],"primary_cat":"math.OC","authors_text":"Akiko Takeda, Kanji Sato, Reiichiro Kawai, Taiji Suzuki","submitted_at":"2022-03-19T02:08:24Z","abstract_excerpt":"Gradient Langevin dynamics and a variety of its variants have attracted increasing attention owing to their convergence towards the global optimal solution, initially in the unconstrained convex framework while recently even in convex constrained non-convex problems. In the present work, we extend those frameworks to non-convex problems on a non-convex feasible region with a global optimization algorithm built upon reflected gradient Langevin dynamics and derive its convergence rates. By effectively making use of its reflection at the boundary in combination with the probabilistic representati"},"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":"2203.10215","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2022-03-19T02:08:24Z","cross_cats_sorted":["math.PR","stat.ML"],"title_canon_sha256":"ca9a96e2967f7b7ba53dae0e5a7e91b7b195e1b649cc2819058c0bf43e636a94","abstract_canon_sha256":"e8921b604f030ea95f6af9c12671bf25bb091d7ab6c3e9b3690e0206b5e705eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:05.808728Z","signature_b64":"BkXsJVCrVJfYrH9Y6KN+NCvEcrZrdW1FKQFss12rho2w2d7VF8oQO/GI62/ZKBhSiYVcSdx9BJbZNGr+IXqFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f3125e98bf40be0f3e77d47e738822fa4a1b6cac51389f1014861925d99dea1","last_reissued_at":"2026-07-05T08:55:05.808254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:05.808254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence Error Analysis of Reflected Gradient Langevin Dynamics for Globally Optimizing Non-Convex Constrained Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.PR","stat.ML"],"primary_cat":"math.OC","authors_text":"Akiko Takeda, Kanji Sato, Reiichiro Kawai, Taiji Suzuki","submitted_at":"2022-03-19T02:08:24Z","abstract_excerpt":"Gradient Langevin dynamics and a variety of its variants have attracted increasing attention owing to their convergence towards the global optimal solution, initially in the unconstrained convex framework while recently even in convex constrained non-convex problems. In the present work, we extend those frameworks to non-convex problems on a non-convex feasible region with a global optimization algorithm built upon reflected gradient Langevin dynamics and derive its convergence rates. By effectively making use of its reflection at the boundary in combination with the probabilistic representati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10215","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/2203.10215/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":"2203.10215","created_at":"2026-07-05T08:55:05.808310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.10215v3","created_at":"2026-07-05T08:55:05.808310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10215","created_at":"2026-07-05T08:55:05.808310+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4YSL2ML6QF6","created_at":"2026-07-05T08:55:05.808310+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4YSL2ML6QF6B47H","created_at":"2026-07-05T08:55:05.808310+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4YSL2ML","created_at":"2026-07-05T08:55:05.808310+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05520","citing_title":"Bayesian Rain Field Reconstruction using Commercial Microwave Links and Diffusion Model Priors","ref_index":75,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L4YSL2ML6QF6B47HPVD6OOECF6","json":"https://pith.science/pith/L4YSL2ML6QF6B47HPVD6OOECF6.json","graph_json":"https://pith.science/api/pith-number/L4YSL2ML6QF6B47HPVD6OOECF6/graph.json","events_json":"https://pith.science/api/pith-number/L4YSL2ML6QF6B47HPVD6OOECF6/events.json","paper":"https://pith.science/paper/L4YSL2ML"},"agent_actions":{"view_html":"https://pith.science/pith/L4YSL2ML6QF6B47HPVD6OOECF6","download_json":"https://pith.science/pith/L4YSL2ML6QF6B47HPVD6OOECF6.json","view_paper":"https://pith.science/paper/L4YSL2ML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.10215&json=true","fetch_graph":"https://pith.science/api/pith-number/L4YSL2ML6QF6B47HPVD6OOECF6/graph.json","fetch_events":"https://pith.science/api/pith-number/L4YSL2ML6QF6B47HPVD6OOECF6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4YSL2ML6QF6B47HPVD6OOECF6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4YSL2ML6QF6B47HPVD6OOECF6/action/storage_attestation","attest_author":"https://pith.science/pith/L4YSL2ML6QF6B47HPVD6OOECF6/action/author_attestation","sign_citation":"https://pith.science/pith/L4YSL2ML6QF6B47HPVD6OOECF6/action/citation_signature","submit_replication":"https://pith.science/pith/L4YSL2ML6QF6B47HPVD6OOECF6/action/replication_record"}},"created_at":"2026-07-05T08:55:05.808310+00:00","updated_at":"2026-07-05T08:55:05.808310+00:00"}