{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HYV3KU7F57ZRPON7VNQTY3ZAY5","short_pith_number":"pith:HYV3KU7F","schema_version":"1.0","canonical_sha256":"3e2bb553e5eff317b9bfab613c6f20c76bf7a4cafabea8eee0c4f321b7419f68","source":{"kind":"arxiv","id":"1805.01648","version":4},"attestation_state":"computed","paper":{"title":"Sharp convergence rates for Langevin dynamics in the nonconvex setting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR","stat.CO"],"primary_cat":"stat.ML","authors_text":"Michael I. Jordan, Niladri S. Chatterji, Peter L. Bartlett, Xiang Cheng, Yasin Abbasi-Yadkori","submitted_at":"2018-05-04T08:16:00Z","abstract_excerpt":"We study the problem of sampling from a distribution $p^*(x) \\propto \\exp\\left(-U(x)\\right)$, where the function $U$ is $L$-smooth everywhere and $m$-strongly convex outside a ball of radius $R$, but potentially nonconvex inside this ball. We study both overdamped and underdamped Langevin MCMC and establish upper bounds on the number of steps required to obtain a sample from a distribution that is within $\\epsilon$ of $p^*$ in $1$-Wasserstein distance. For the first-order method (overdamped Langevin MCMC), the iteration complexity is $\\tilde{\\mathcal{O}}\\left(e^{cLR^2}d/\\epsilon^2\\right)$, whe"},"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":"1805.01648","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-04T08:16:00Z","cross_cats_sorted":["cs.LG","math.PR","stat.CO"],"title_canon_sha256":"f614a128acb932d4b076c069cd0ece891d43567690596de8b0b5c500a743b0eb","abstract_canon_sha256":"674788b8882aab5d1b31c01e10dd505e62733060ef115e09e897fdd1e7c9af62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:16:06.782664Z","signature_b64":"hrI0SY0GQEfjjtsgenVwzKTvdnB23MHFjC18HnBo4qOGqEkI5AT8J6U6+ljpL7Mx6g5KnGfz56SMGCHr6ZPVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e2bb553e5eff317b9bfab613c6f20c76bf7a4cafabea8eee0c4f321b7419f68","last_reissued_at":"2026-07-05T01:16:06.782197Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:16:06.782197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sharp convergence rates for Langevin dynamics in the nonconvex setting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR","stat.CO"],"primary_cat":"stat.ML","authors_text":"Michael I. Jordan, Niladri S. Chatterji, Peter L. Bartlett, Xiang Cheng, Yasin Abbasi-Yadkori","submitted_at":"2018-05-04T08:16:00Z","abstract_excerpt":"We study the problem of sampling from a distribution $p^*(x) \\propto \\exp\\left(-U(x)\\right)$, where the function $U$ is $L$-smooth everywhere and $m$-strongly convex outside a ball of radius $R$, but potentially nonconvex inside this ball. We study both overdamped and underdamped Langevin MCMC and establish upper bounds on the number of steps required to obtain a sample from a distribution that is within $\\epsilon$ of $p^*$ in $1$-Wasserstein distance. For the first-order method (overdamped Langevin MCMC), the iteration complexity is $\\tilde{\\mathcal{O}}\\left(e^{cLR^2}d/\\epsilon^2\\right)$, whe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.01648","kind":"arxiv","version":4},"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/1805.01648/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":"1805.01648","created_at":"2026-07-05T01:16:06.782268+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.01648v4","created_at":"2026-07-05T01:16:06.782268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.01648","created_at":"2026-07-05T01:16:06.782268+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYV3KU7F57ZR","created_at":"2026-07-05T01:16:06.782268+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYV3KU7F57ZRPON7","created_at":"2026-07-05T01:16:06.782268+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYV3KU7F","created_at":"2026-07-05T01:16:06.782268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31088","citing_title":"On couplings for kinetic Langevin diffusions","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26800","citing_title":"Accelerated Schr\\\"odinger-F\\\"ollmer samplers","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30930","citing_title":"SGD at the Edge of Stability: Stochastic Stabilization with Large Learning Rates","ref_index":153,"is_internal_anchor":false},{"citing_arxiv_id":"2303.03237","citing_title":"Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2407.05790","citing_title":"Kinetic Interacting Particle Langevin Monte Carlo","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2503.19066","citing_title":"Accelerating Langevin Monte Carlo Sampling: A Large Deviations Analysis","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2603.00773","citing_title":"Long-time $L^p$ Wasserstein contraction for diffusion processes without global dissipativity","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10775","citing_title":"On the global convergence of gradient flow for wide shallow models beyond homogeneous nonlinearities","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10373","citing_title":"Shuffling the Data, Stretching the Step-size: Sharper Bias in constant step-size SGD","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07939","citing_title":"Accelerating Langevin Monte Carlo via Efficient Stochastic Runge--Kutta Methods beyond Log-Concavity","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HYV3KU7F57ZRPON7VNQTY3ZAY5","json":"https://pith.science/pith/HYV3KU7F57ZRPON7VNQTY3ZAY5.json","graph_json":"https://pith.science/api/pith-number/HYV3KU7F57ZRPON7VNQTY3ZAY5/graph.json","events_json":"https://pith.science/api/pith-number/HYV3KU7F57ZRPON7VNQTY3ZAY5/events.json","paper":"https://pith.science/paper/HYV3KU7F"},"agent_actions":{"view_html":"https://pith.science/pith/HYV3KU7F57ZRPON7VNQTY3ZAY5","download_json":"https://pith.science/pith/HYV3KU7F57ZRPON7VNQTY3ZAY5.json","view_paper":"https://pith.science/paper/HYV3KU7F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.01648&json=true","fetch_graph":"https://pith.science/api/pith-number/HYV3KU7F57ZRPON7VNQTY3ZAY5/graph.json","fetch_events":"https://pith.science/api/pith-number/HYV3KU7F57ZRPON7VNQTY3ZAY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYV3KU7F57ZRPON7VNQTY3ZAY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYV3KU7F57ZRPON7VNQTY3ZAY5/action/storage_attestation","attest_author":"https://pith.science/pith/HYV3KU7F57ZRPON7VNQTY3ZAY5/action/author_attestation","sign_citation":"https://pith.science/pith/HYV3KU7F57ZRPON7VNQTY3ZAY5/action/citation_signature","submit_replication":"https://pith.science/pith/HYV3KU7F57ZRPON7VNQTY3ZAY5/action/replication_record"}},"created_at":"2026-07-05T01:16:06.782268+00:00","updated_at":"2026-07-05T01:16:06.782268+00:00"}