{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KUKLP45QPVNO7VUEY4AGZ4FCHU","short_pith_number":"pith:KUKLP45Q","schema_version":"1.0","canonical_sha256":"5514b7f3b07d5aefd684c7006cf0a23d3607506106d09b4640760303328aee0a","source":{"kind":"arxiv","id":"2505.01937","version":1},"attestation_state":"computed","paper":{"title":"Faster logconcave sampling from a cold start in high dimension","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.FA","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"Santosh S. Vempala, Yunbum Kook","submitted_at":"2025-05-03T22:14:04Z","abstract_excerpt":"We present a faster algorithm to generate a warm start for sampling an arbitrary logconcave density specified by an evaluation oracle, leading to the first sub-cubic sampling algorithms for inputs in (near-)isotropic position. A long line of prior work incurred a warm-start penalty of at least linear in the dimension, hitting a cubic barrier, even for the special case of uniform sampling from convex bodies.\n  Our improvement relies on two key ingredients of independent interest. (1) We show how to sample given a warm start in weaker notions of distance, in particular $q$-R\\'enyi divergence for"},"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":"2505.01937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2025-05-03T22:14:04Z","cross_cats_sorted":["cs.LG","math.FA","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"c918216eabe7f8dccfba84cde74eec88260bdd0b1bf917396657983d70ee97d5","abstract_canon_sha256":"21a941f7be2f747695bc1ce307237f5de6557a1600b1cc6e6b7464e55d532380"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:28.752140Z","signature_b64":"avssPG3R3Yl4mlBlMsap1z9bp51V/mkbFmRKSYKNdzVhiNNSW5giwF0Tv5kmINgcb4bnZh+Qe6poQmyd/Co3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5514b7f3b07d5aefd684c7006cf0a23d3607506106d09b4640760303328aee0a","last_reissued_at":"2026-07-05T10:58:28.751598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:28.751598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faster logconcave sampling from a cold start in high dimension","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.FA","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"Santosh S. Vempala, Yunbum Kook","submitted_at":"2025-05-03T22:14:04Z","abstract_excerpt":"We present a faster algorithm to generate a warm start for sampling an arbitrary logconcave density specified by an evaluation oracle, leading to the first sub-cubic sampling algorithms for inputs in (near-)isotropic position. A long line of prior work incurred a warm-start penalty of at least linear in the dimension, hitting a cubic barrier, even for the special case of uniform sampling from convex bodies.\n  Our improvement relies on two key ingredients of independent interest. (1) We show how to sample given a warm start in weaker notions of distance, in particular $q$-R\\'enyi divergence for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01937","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/2505.01937/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":"2505.01937","created_at":"2026-07-05T10:58:28.751662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01937v1","created_at":"2026-07-05T10:58:28.751662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01937","created_at":"2026-07-05T10:58:28.751662+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUKLP45QPVNO","created_at":"2026-07-05T10:58:28.751662+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUKLP45QPVNO7VUE","created_at":"2026-07-05T10:58:28.751662+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUKLP45Q","created_at":"2026-07-05T10:58:28.751662+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12461","citing_title":"A proximal gradient algorithm for composite log-concave sampling","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KUKLP45QPVNO7VUEY4AGZ4FCHU","json":"https://pith.science/pith/KUKLP45QPVNO7VUEY4AGZ4FCHU.json","graph_json":"https://pith.science/api/pith-number/KUKLP45QPVNO7VUEY4AGZ4FCHU/graph.json","events_json":"https://pith.science/api/pith-number/KUKLP45QPVNO7VUEY4AGZ4FCHU/events.json","paper":"https://pith.science/paper/KUKLP45Q"},"agent_actions":{"view_html":"https://pith.science/pith/KUKLP45QPVNO7VUEY4AGZ4FCHU","download_json":"https://pith.science/pith/KUKLP45QPVNO7VUEY4AGZ4FCHU.json","view_paper":"https://pith.science/paper/KUKLP45Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01937&json=true","fetch_graph":"https://pith.science/api/pith-number/KUKLP45QPVNO7VUEY4AGZ4FCHU/graph.json","fetch_events":"https://pith.science/api/pith-number/KUKLP45QPVNO7VUEY4AGZ4FCHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUKLP45QPVNO7VUEY4AGZ4FCHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUKLP45QPVNO7VUEY4AGZ4FCHU/action/storage_attestation","attest_author":"https://pith.science/pith/KUKLP45QPVNO7VUEY4AGZ4FCHU/action/author_attestation","sign_citation":"https://pith.science/pith/KUKLP45QPVNO7VUEY4AGZ4FCHU/action/citation_signature","submit_replication":"https://pith.science/pith/KUKLP45QPVNO7VUEY4AGZ4FCHU/action/replication_record"}},"created_at":"2026-07-05T10:58:28.751662+00:00","updated_at":"2026-07-05T10:58:28.751662+00:00"}