{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N7AAT6MH7C75MKDFID7NWXHWUY","short_pith_number":"pith:N7AAT6MH","schema_version":"1.0","canonical_sha256":"6fc009f987f8bfd6286540fedb5cf6a621cb0b8fd760b48b5b9c5555ef7852ed","source":{"kind":"arxiv","id":"2410.13738","version":2},"attestation_state":"computed","paper":{"title":"Instance-dependent Convergence Theory for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Gen Li, Yuchen Jiao","submitted_at":"2024-10-17T16:37:33Z","abstract_excerpt":"Score-based diffusion models have demonstrated outstanding empirical performance in machine learning and artificial intelligence, particularly in generating high-quality new samples from complex probability distributions. Improving the theoretical understanding of diffusion models, with a particular focus on the convergence analysis, has attracted significant attention. In this work, we develop a convergence rate that is adaptive to the smoothness of different target distributions, referred to as instance-dependent bound. Specifically, we establish an iteration complexity of $\\min\\{d,d^{2/3}L^"},"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":"2410.13738","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-17T16:37:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3ee7efcad0344cbf34d87cd6ecad21141580e7496a746028844753c966c82b56","abstract_canon_sha256":"56c83387803e0807a3949328f7eece40c17af860ee013ff1e57e3463f3639294"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:36.057914Z","signature_b64":"2HR6SYAS4Qd6UQTGuRNvJawP3SunAYELRHJeeMntnj2w4nUg52VXBWIxPy4RBXpuy2H4fsYsmnvvuJTAemQjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fc009f987f8bfd6286540fedb5cf6a621cb0b8fd760b48b5b9c5555ef7852ed","last_reissued_at":"2026-07-05T11:11:36.057284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:36.057284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instance-dependent Convergence Theory for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Gen Li, Yuchen Jiao","submitted_at":"2024-10-17T16:37:33Z","abstract_excerpt":"Score-based diffusion models have demonstrated outstanding empirical performance in machine learning and artificial intelligence, particularly in generating high-quality new samples from complex probability distributions. Improving the theoretical understanding of diffusion models, with a particular focus on the convergence analysis, has attracted significant attention. In this work, we develop a convergence rate that is adaptive to the smoothness of different target distributions, referred to as instance-dependent bound. Specifically, we establish an iteration complexity of $\\min\\{d,d^{2/3}L^"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13738","kind":"arxiv","version":2},"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/2410.13738/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":"2410.13738","created_at":"2026-07-05T11:11:36.057353+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13738v2","created_at":"2026-07-05T11:11:36.057353+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13738","created_at":"2026-07-05T11:11:36.057353+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7AAT6MH7C75","created_at":"2026-07-05T11:11:36.057353+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7AAT6MH7C75MKDF","created_at":"2026-07-05T11:11:36.057353+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7AAT6MH","created_at":"2026-07-05T11:11:36.057353+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23627","citing_title":"Diffusion Models Adapt to Low-Dimensional Structure Under Flexible Coefficient Choices","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27769","citing_title":"Smoothed Score Queries and the Complexity of Sampling","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N7AAT6MH7C75MKDFID7NWXHWUY","json":"https://pith.science/pith/N7AAT6MH7C75MKDFID7NWXHWUY.json","graph_json":"https://pith.science/api/pith-number/N7AAT6MH7C75MKDFID7NWXHWUY/graph.json","events_json":"https://pith.science/api/pith-number/N7AAT6MH7C75MKDFID7NWXHWUY/events.json","paper":"https://pith.science/paper/N7AAT6MH"},"agent_actions":{"view_html":"https://pith.science/pith/N7AAT6MH7C75MKDFID7NWXHWUY","download_json":"https://pith.science/pith/N7AAT6MH7C75MKDFID7NWXHWUY.json","view_paper":"https://pith.science/paper/N7AAT6MH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13738&json=true","fetch_graph":"https://pith.science/api/pith-number/N7AAT6MH7C75MKDFID7NWXHWUY/graph.json","fetch_events":"https://pith.science/api/pith-number/N7AAT6MH7C75MKDFID7NWXHWUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7AAT6MH7C75MKDFID7NWXHWUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7AAT6MH7C75MKDFID7NWXHWUY/action/storage_attestation","attest_author":"https://pith.science/pith/N7AAT6MH7C75MKDFID7NWXHWUY/action/author_attestation","sign_citation":"https://pith.science/pith/N7AAT6MH7C75MKDFID7NWXHWUY/action/citation_signature","submit_replication":"https://pith.science/pith/N7AAT6MH7C75MKDFID7NWXHWUY/action/replication_record"}},"created_at":"2026-07-05T11:11:36.057353+00:00","updated_at":"2026-07-05T11:11:36.057353+00:00"}