{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KFF3UKMKXEVJI76V2XTMPNJFMR","short_pith_number":"pith:KFF3UKMK","schema_version":"1.0","canonical_sha256":"514bba298ab92a947fd5d5e6c7b5256471eb71c31a69b10e72b6dc99824d13fe","source":{"kind":"arxiv","id":"2403.03852","version":1},"attestation_state":"computed","paper":{"title":"Accelerating Convergence of Score-Based Diffusion Models, Provably","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gen Li, Timofey Efimov, Yuejie Chi, Yu Huang, Yuting Wei, Yuxin Chen","submitted_at":"2024-03-06T17:02:39Z","abstract_excerpt":"Score-based diffusion models, while achieving remarkable empirical performance, often suffer from low sampling speed, due to extensive function evaluations needed during the sampling phase. Despite a flurry of recent activities towards speeding up diffusion generative modeling in practice, theoretical underpinnings for acceleration techniques remain severely limited. In this paper, we design novel training-free algorithms to accelerate popular deterministic (i.e., DDIM) and stochastic (i.e., DDPM) samplers. Our accelerated deterministic sampler converges at a rate $O(1/{T}^2)$ with $T$ the num"},"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":"2403.03852","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-06T17:02:39Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","math.OC","stat.ML"],"title_canon_sha256":"559bbadce8e69fb87a7bbd4beccc89007ea55a211e5f669e2b086a4f5494e117","abstract_canon_sha256":"0199721aeec7851db86cb76bcf2bb16b82aefe8829cf6781f72f147656336d4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:02.309191Z","signature_b64":"nyJre2//UcJexsJxVC7Q77aRuFr3xNmzUGsnxKcYJe/n60fm2rz2Y122PzI1YF3AHD0yXBuU8q+18bmd3mk1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"514bba298ab92a947fd5d5e6c7b5256471eb71c31a69b10e72b6dc99824d13fe","last_reissued_at":"2026-07-05T07:53:02.308797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:02.308797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Convergence of Score-Based Diffusion Models, Provably","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gen Li, Timofey Efimov, Yuejie Chi, Yu Huang, Yuting Wei, Yuxin Chen","submitted_at":"2024-03-06T17:02:39Z","abstract_excerpt":"Score-based diffusion models, while achieving remarkable empirical performance, often suffer from low sampling speed, due to extensive function evaluations needed during the sampling phase. Despite a flurry of recent activities towards speeding up diffusion generative modeling in practice, theoretical underpinnings for acceleration techniques remain severely limited. In this paper, we design novel training-free algorithms to accelerate popular deterministic (i.e., DDIM) and stochastic (i.e., DDPM) samplers. Our accelerated deterministic sampler converges at a rate $O(1/{T}^2)$ with $T$ the num"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03852","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/2403.03852/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":"2403.03852","created_at":"2026-07-05T07:53:02.308854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03852v1","created_at":"2026-07-05T07:53:02.308854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03852","created_at":"2026-07-05T07:53:02.308854+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFF3UKMKXEVJ","created_at":"2026-07-05T07:53:02.308854+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFF3UKMKXEVJI76V","created_at":"2026-07-05T07:53:02.308854+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFF3UKMK","created_at":"2026-07-05T07:53:02.308854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"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":30,"is_internal_anchor":false},{"citing_arxiv_id":"2509.01629","citing_title":"Lipschitz-Guided Design of Interpolation Schedules in Generative Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13278","citing_title":"Proximal-Based Generative Modeling for Bayesian Inverse Problems","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KFF3UKMKXEVJI76V2XTMPNJFMR","json":"https://pith.science/pith/KFF3UKMKXEVJI76V2XTMPNJFMR.json","graph_json":"https://pith.science/api/pith-number/KFF3UKMKXEVJI76V2XTMPNJFMR/graph.json","events_json":"https://pith.science/api/pith-number/KFF3UKMKXEVJI76V2XTMPNJFMR/events.json","paper":"https://pith.science/paper/KFF3UKMK"},"agent_actions":{"view_html":"https://pith.science/pith/KFF3UKMKXEVJI76V2XTMPNJFMR","download_json":"https://pith.science/pith/KFF3UKMKXEVJI76V2XTMPNJFMR.json","view_paper":"https://pith.science/paper/KFF3UKMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03852&json=true","fetch_graph":"https://pith.science/api/pith-number/KFF3UKMKXEVJI76V2XTMPNJFMR/graph.json","fetch_events":"https://pith.science/api/pith-number/KFF3UKMKXEVJI76V2XTMPNJFMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFF3UKMKXEVJI76V2XTMPNJFMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFF3UKMKXEVJI76V2XTMPNJFMR/action/storage_attestation","attest_author":"https://pith.science/pith/KFF3UKMKXEVJI76V2XTMPNJFMR/action/author_attestation","sign_citation":"https://pith.science/pith/KFF3UKMKXEVJI76V2XTMPNJFMR/action/citation_signature","submit_replication":"https://pith.science/pith/KFF3UKMKXEVJI76V2XTMPNJFMR/action/replication_record"}},"created_at":"2026-07-05T07:53:02.308854+00:00","updated_at":"2026-07-05T07:53:02.308854+00:00"}