{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H6ZXHZVVEGXPRZB6SYWTTC6LIS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4d5e0168c25bd96cddc96cb32677b55c7590b83ebd0bbf3bd040d58753a87c11","cross_cats_sorted":["cs.LG","math.PR","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-06-05T10:51:18Z","title_canon_sha256":"1ae6c9b57436a77661f6512e1bf0d22d7fac3285667f6de0dbb9b18be90d53df"},"schema_version":"1.0","source":{"id":"2506.04878","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04878","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04878v1","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04878","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"pith_short_12","alias_value":"H6ZXHZVVEGXP","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"pith_short_16","alias_value":"H6ZXHZVVEGXPRZB6","created_at":"2026-07-05T11:16:38Z"},{"alias_kind":"pith_short_8","alias_value":"H6ZXHZVV","created_at":"2026-07-05T11:16:38Z"}],"graph_snapshots":[{"event_id":"sha256:fdf4b656448d747ca01ca7d30e1c0e69a8da9ceddf18699c213adbafc88acf63","target":"graph","created_at":"2026-07-05T11:16:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.04878/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Motivated by applications in deep learning, where the global Lipschitz continuity condition is often not satisfied, we examine the problem of sampling from distributions with super-linearly growing log-gradients. We propose a novel tamed Langevin dynamics-based algorithm, called kTULA, to solve the aforementioned sampling problem, and provide a theoretical guarantee for its performance. More precisely, we establish a non-asymptotic convergence bound in Kullback-Leibler (KL) divergence with the best-known rate of convergence equal to $2-\\overline{\\epsilon}$, $\\overline{\\epsilon}>0$, which signi","authors_text":"Iosif Lytras, Sotirios Sabanis, Ying Zhang","cross_cats":["cs.LG","math.PR","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-06-05T10:51:18Z","title":"kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04878","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e1ee3a56ef55286b7f9b7c1b503d6ec1837a81fd764e19e1e0d7d6ab8f69837f","target":"record","created_at":"2026-07-05T11:16:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4d5e0168c25bd96cddc96cb32677b55c7590b83ebd0bbf3bd040d58753a87c11","cross_cats_sorted":["cs.LG","math.PR","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2025-06-05T10:51:18Z","title_canon_sha256":"1ae6c9b57436a77661f6512e1bf0d22d7fac3285667f6de0dbb9b18be90d53df"},"schema_version":"1.0","source":{"id":"2506.04878","kind":"arxiv","version":1}},"canonical_sha256":"3fb373e6b521aef8e43e962d398bcb449ec943aa4f86cde63f50eb81cac90d7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fb373e6b521aef8e43e962d398bcb449ec943aa4f86cde63f50eb81cac90d7c","first_computed_at":"2026-07-05T11:16:38.408311Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:38.408311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6udcnDK8NMkwyZGb9FKIH9SNUOueGNCeBTIfSkgX/9ubOiKFUpMPLmoraNlULVv70oy8XB4su5DY+9fIrZ94Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:38.408858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04878","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1ee3a56ef55286b7f9b7c1b503d6ec1837a81fd764e19e1e0d7d6ab8f69837f","sha256:fdf4b656448d747ca01ca7d30e1c0e69a8da9ceddf18699c213adbafc88acf63"],"state_sha256":"8edecf4e97b3f9f4546c1bbd1b3530cad3791e23c8279508eceb0ae4ca249a38"}