{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N2HX2ETED37GRSVEKWMCEF5GGC","short_pith_number":"pith:N2HX2ETE","schema_version":"1.0","canonical_sha256":"6e8f7d12641efe68caa455982217a630adcf0650bbb7c5669bdad61970f219be","source":{"kind":"arxiv","id":"2408.02320","version":1},"attestation_state":"computed","paper":{"title":"A Sharp Convergence Theory for The Probability Flow ODEs of Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","eess.SP","math.NA","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Gen Li, Yuejie Chi, Yuting Wei, Yuxin Chen","submitted_at":"2024-08-05T09:02:24Z","abstract_excerpt":"Diffusion models, which convert noise into new data instances by learning to reverse a diffusion process, have become a cornerstone in contemporary generative modeling. In this work, we develop non-asymptotic convergence theory for a popular diffusion-based sampler (i.e., the probability flow ODE sampler) in discrete time, assuming access to $\\ell_2$-accurate estimates of the (Stein) score functions. For distributions in $\\mathbb{R}^d$, we prove that $d/\\varepsilon$ iterations -- modulo some logarithmic and lower-order terms -- are sufficient to approximate the target distribution to within $\\"},"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":"2408.02320","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-05T09:02:24Z","cross_cats_sorted":["cs.NA","eess.SP","math.NA","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"f6bc32868aaad1390a8702ca8c050ee0eb047005c5e920f38eeb614ea0b99e93","abstract_canon_sha256":"684057382d52d6bd3e39e741786cddf3ae56f4882cdf8489c56d4ddce7c8f458"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:11.326985Z","signature_b64":"PCxTvjgXwrfV0i0Dkf8p5vk3px/sFlwjaOXpW1BXmCcdo/AeTfB6RVU8KRtukxu8Du7IHCJUfkowXa6M2VBbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e8f7d12641efe68caa455982217a630adcf0650bbb7c5669bdad61970f219be","last_reissued_at":"2026-07-05T08:52:11.326392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:11.326392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Sharp Convergence Theory for The Probability Flow ODEs of Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","eess.SP","math.NA","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Gen Li, Yuejie Chi, Yuting Wei, Yuxin Chen","submitted_at":"2024-08-05T09:02:24Z","abstract_excerpt":"Diffusion models, which convert noise into new data instances by learning to reverse a diffusion process, have become a cornerstone in contemporary generative modeling. In this work, we develop non-asymptotic convergence theory for a popular diffusion-based sampler (i.e., the probability flow ODE sampler) in discrete time, assuming access to $\\ell_2$-accurate estimates of the (Stein) score functions. For distributions in $\\mathbb{R}^d$, we prove that $d/\\varepsilon$ iterations -- modulo some logarithmic and lower-order terms -- are sufficient to approximate the target distribution to within $\\"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02320","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/2408.02320/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":"2408.02320","created_at":"2026-07-05T08:52:11.326471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02320v1","created_at":"2026-07-05T08:52:11.326471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02320","created_at":"2026-07-05T08:52:11.326471+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2HX2ETED37G","created_at":"2026-07-05T08:52:11.326471+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2HX2ETED37GRSVE","created_at":"2026-07-05T08:52:11.326471+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2HX2ETE","created_at":"2026-07-05T08:52:11.326471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10353","citing_title":"Higher-order Diffusion Sampling via Chebyshev Interpolation and Gauss--Seidel Iterations","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2505.18344","citing_title":"Improved Sample Complexity For Diffusion Model Training Without Empirical Risk Minimizer Access","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07969","citing_title":"When Diffusion Model Can Ignore Dimension: An Entropy-Based Theory","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2HX2ETED37GRSVEKWMCEF5GGC","json":"https://pith.science/pith/N2HX2ETED37GRSVEKWMCEF5GGC.json","graph_json":"https://pith.science/api/pith-number/N2HX2ETED37GRSVEKWMCEF5GGC/graph.json","events_json":"https://pith.science/api/pith-number/N2HX2ETED37GRSVEKWMCEF5GGC/events.json","paper":"https://pith.science/paper/N2HX2ETE"},"agent_actions":{"view_html":"https://pith.science/pith/N2HX2ETED37GRSVEKWMCEF5GGC","download_json":"https://pith.science/pith/N2HX2ETED37GRSVEKWMCEF5GGC.json","view_paper":"https://pith.science/paper/N2HX2ETE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02320&json=true","fetch_graph":"https://pith.science/api/pith-number/N2HX2ETED37GRSVEKWMCEF5GGC/graph.json","fetch_events":"https://pith.science/api/pith-number/N2HX2ETED37GRSVEKWMCEF5GGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2HX2ETED37GRSVEKWMCEF5GGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2HX2ETED37GRSVEKWMCEF5GGC/action/storage_attestation","attest_author":"https://pith.science/pith/N2HX2ETED37GRSVEKWMCEF5GGC/action/author_attestation","sign_citation":"https://pith.science/pith/N2HX2ETED37GRSVEKWMCEF5GGC/action/citation_signature","submit_replication":"https://pith.science/pith/N2HX2ETED37GRSVEKWMCEF5GGC/action/replication_record"}},"created_at":"2026-07-05T08:52:11.326471+00:00","updated_at":"2026-07-05T08:52:11.326471+00:00"}