{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IIDMPURII5JEGHXMXMQ4TXO5HW","short_pith_number":"pith:IIDMPURI","schema_version":"1.0","canonical_sha256":"4206c7d2284752431eecbb21c9dddd3d90a3175d0cf8170f5288c4b05c980092","source":{"kind":"arxiv","id":"2405.16387","version":1},"attestation_state":"computed","paper":{"title":"Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Difan Zou, HanZe Dong, Tong Zhang, Xunpeng Huang, Yi-An Ma, Yi Zhang","submitted_at":"2024-05-26T00:26:57Z","abstract_excerpt":"To generate data from trained diffusion models, most inference algorithms, such as DDPM, DDIM, and other variants, rely on discretizing the reverse SDEs or their equivalent ODEs. In this paper, we view such approaches as decomposing the entire denoising diffusion process into several segments, each corresponding to a reverse transition kernel (RTK) sampling subproblem. Specifically, DDPM uses a Gaussian approximation for the RTK, resulting in low per-subproblem complexity but requiring a large number of segments (i.e., subproblems), which is conjectured to be inefficient. To address this, we d"},"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":"2405.16387","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-26T00:26:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f5a76ee663f769a74badad49f38af4310ce5a782226a1a1662f91c5d9c86b2e6","abstract_canon_sha256":"43a7b27a085a8d2a5c5fe4ca33751884ac42f095b47cd6086ffb2a31a4a5451d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:29.482365Z","signature_b64":"SLXHuzipyQ7W1lTapnSUUrf53IL5oG8PAhZU+Xlg4DC9PjcNdPTnmneBW4uFIn8425+NMJ60KZgR9k7UT73QCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4206c7d2284752431eecbb21c9dddd3d90a3175d0cf8170f5288c4b05c980092","last_reissued_at":"2026-07-05T08:23:29.481869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:29.481869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Difan Zou, HanZe Dong, Tong Zhang, Xunpeng Huang, Yi-An Ma, Yi Zhang","submitted_at":"2024-05-26T00:26:57Z","abstract_excerpt":"To generate data from trained diffusion models, most inference algorithms, such as DDPM, DDIM, and other variants, rely on discretizing the reverse SDEs or their equivalent ODEs. In this paper, we view such approaches as decomposing the entire denoising diffusion process into several segments, each corresponding to a reverse transition kernel (RTK) sampling subproblem. Specifically, DDPM uses a Gaussian approximation for the RTK, resulting in low per-subproblem complexity but requiring a large number of segments (i.e., subproblems), which is conjectured to be inefficient. To address this, we d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16387","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/2405.16387/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":"2405.16387","created_at":"2026-07-05T08:23:29.481931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16387v1","created_at":"2026-07-05T08:23:29.481931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16387","created_at":"2026-07-05T08:23:29.481931+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIDMPURII5JE","created_at":"2026-07-05T08:23:29.481931+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIDMPURII5JEGHXM","created_at":"2026-07-05T08:23:29.481931+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIDMPURI","created_at":"2026-07-05T08:23:29.481931+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"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":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIDMPURII5JEGHXMXMQ4TXO5HW","json":"https://pith.science/pith/IIDMPURII5JEGHXMXMQ4TXO5HW.json","graph_json":"https://pith.science/api/pith-number/IIDMPURII5JEGHXMXMQ4TXO5HW/graph.json","events_json":"https://pith.science/api/pith-number/IIDMPURII5JEGHXMXMQ4TXO5HW/events.json","paper":"https://pith.science/paper/IIDMPURI"},"agent_actions":{"view_html":"https://pith.science/pith/IIDMPURII5JEGHXMXMQ4TXO5HW","download_json":"https://pith.science/pith/IIDMPURII5JEGHXMXMQ4TXO5HW.json","view_paper":"https://pith.science/paper/IIDMPURI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16387&json=true","fetch_graph":"https://pith.science/api/pith-number/IIDMPURII5JEGHXMXMQ4TXO5HW/graph.json","fetch_events":"https://pith.science/api/pith-number/IIDMPURII5JEGHXMXMQ4TXO5HW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIDMPURII5JEGHXMXMQ4TXO5HW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIDMPURII5JEGHXMXMQ4TXO5HW/action/storage_attestation","attest_author":"https://pith.science/pith/IIDMPURII5JEGHXMXMQ4TXO5HW/action/author_attestation","sign_citation":"https://pith.science/pith/IIDMPURII5JEGHXMXMQ4TXO5HW/action/citation_signature","submit_replication":"https://pith.science/pith/IIDMPURII5JEGHXMXMQ4TXO5HW/action/replication_record"}},"created_at":"2026-07-05T08:23:29.481931+00:00","updated_at":"2026-07-05T08:23:29.481931+00:00"}