{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3YTCALSL64A7HGJOQ2MBI55GR4","short_pith_number":"pith:3YTCALSL","schema_version":"1.0","canonical_sha256":"de26202e4bf701f3992e86981477a68f051f7232d068ddee4439b31b371ae8bb","source":{"kind":"arxiv","id":"2405.17693","version":1},"attestation_state":"computed","paper":{"title":"Tamed Langevin sampling under weaker conditions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","math.OC","math.PR"],"primary_cat":"stat.ML","authors_text":"Iosif Lytras, Panayotis Mertikopoulos","submitted_at":"2024-05-27T23:00:40Z","abstract_excerpt":"Motivated by applications to deep learning which often fail standard Lipschitz smoothness requirements, we examine the problem of sampling from distributions that are not log-concave and are only weakly dissipative, with log-gradients allowed to grow superlinearly at infinity. In terms of structure, we only assume that the target distribution satisfies either a log-Sobolev or a Poincar\\'e inequality and a local Lipschitz smoothness assumption with modulus growing possibly polynomially at infinity. This set of assumptions greatly exceeds the operational limits of the \"vanilla\" unadjusted Langev"},"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":"2405.17693","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-27T23:00:40Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA","math.OC","math.PR"],"title_canon_sha256":"44241114e628a521be3244aef610f56108dd433d8d929cc64d8b8cc753f9cf02","abstract_canon_sha256":"6548b77cc65d027bf791152fe294eeb6e1ee8b1a8e24791e2e86f85dc64685fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:09.837074Z","signature_b64":"XeQ27TNVwd2npXxki8GKxA2Vr7EPSy62I4wRJc8YyHLHHvF4ehAbzGMCHucLJF9TGAM6cqVISnktVOGSkvXjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de26202e4bf701f3992e86981477a68f051f7232d068ddee4439b31b371ae8bb","last_reissued_at":"2026-07-05T08:24:09.836598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:09.836598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tamed Langevin sampling under weaker conditions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","math.OC","math.PR"],"primary_cat":"stat.ML","authors_text":"Iosif Lytras, Panayotis Mertikopoulos","submitted_at":"2024-05-27T23:00:40Z","abstract_excerpt":"Motivated by applications to deep learning which often fail standard Lipschitz smoothness requirements, we examine the problem of sampling from distributions that are not log-concave and are only weakly dissipative, with log-gradients allowed to grow superlinearly at infinity. In terms of structure, we only assume that the target distribution satisfies either a log-Sobolev or a Poincar\\'e inequality and a local Lipschitz smoothness assumption with modulus growing possibly polynomially at infinity. This set of assumptions greatly exceeds the operational limits of the \"vanilla\" unadjusted Langev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17693","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.17693/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":"2405.17693","created_at":"2026-07-05T08:24:09.836657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17693v1","created_at":"2026-07-05T08:24:09.836657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17693","created_at":"2026-07-05T08:24:09.836657+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YTCALSL64A7","created_at":"2026-07-05T08:24:09.836657+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YTCALSL64A7HGJO","created_at":"2026-07-05T08:24:09.836657+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YTCALSL","created_at":"2026-07-05T08:24:09.836657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10559","citing_title":"Deterministic Denominator Design for Localized Tamed Stochastic Gradient Langevin Dynamics","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24937","citing_title":"Error estimates for tamed Euler and Randomized Euler schemes for SDEs with locally Lipschitz drift with applications to non-logconcave sampling and optimization","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2406.09241","citing_title":"What is the long-run distribution of stochastic gradient descent? A large deviations analysis","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25630","citing_title":"When Langevin Monte Carlo Meets Randomization: New Sampling Algorithms with Non-asymptotic Error Bounds beyond Log-Concavity and Gradient Lipschitzness","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YTCALSL64A7HGJOQ2MBI55GR4","json":"https://pith.science/pith/3YTCALSL64A7HGJOQ2MBI55GR4.json","graph_json":"https://pith.science/api/pith-number/3YTCALSL64A7HGJOQ2MBI55GR4/graph.json","events_json":"https://pith.science/api/pith-number/3YTCALSL64A7HGJOQ2MBI55GR4/events.json","paper":"https://pith.science/paper/3YTCALSL"},"agent_actions":{"view_html":"https://pith.science/pith/3YTCALSL64A7HGJOQ2MBI55GR4","download_json":"https://pith.science/pith/3YTCALSL64A7HGJOQ2MBI55GR4.json","view_paper":"https://pith.science/paper/3YTCALSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17693&json=true","fetch_graph":"https://pith.science/api/pith-number/3YTCALSL64A7HGJOQ2MBI55GR4/graph.json","fetch_events":"https://pith.science/api/pith-number/3YTCALSL64A7HGJOQ2MBI55GR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YTCALSL64A7HGJOQ2MBI55GR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YTCALSL64A7HGJOQ2MBI55GR4/action/storage_attestation","attest_author":"https://pith.science/pith/3YTCALSL64A7HGJOQ2MBI55GR4/action/author_attestation","sign_citation":"https://pith.science/pith/3YTCALSL64A7HGJOQ2MBI55GR4/action/citation_signature","submit_replication":"https://pith.science/pith/3YTCALSL64A7HGJOQ2MBI55GR4/action/replication_record"}},"created_at":"2026-07-05T08:24:09.836657+00:00","updated_at":"2026-07-05T08:24:09.836657+00:00"}