{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IKUNQV466PFAGA2LP3RDFKJUWT","short_pith_number":"pith:IKUNQV46","schema_version":"1.0","canonical_sha256":"42a8d8579ef3ca03034b7ee232a934b4f1d7f90abf4476d67d6231cb372cefad","source":{"kind":"arxiv","id":"2002.00107","version":4},"attestation_state":"computed","paper":{"title":"Generative Modeling with Denoising Auto-Encoders and Langevin Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Adam Block, Alexander Rakhlin, Youssef Mroueh","submitted_at":"2020-01-31T23:50:03Z","abstract_excerpt":"We study convergence of a generative modeling method that first estimates the score function of the distribution using Denoising Auto-Encoders (DAE) or Denoising Score Matching (DSM) and then employs Langevin diffusion for sampling. We show that both DAE and DSM provide estimates of the score of the Gaussian smoothed population density, allowing us to apply the machinery of Empirical Processes.\n  We overcome the challenge of relying only on $L^2$ bounds on the score estimation error and provide finite-sample bounds in the Wasserstein distance between the law of the population distribution and "},"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":"2002.00107","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-01-31T23:50:03Z","cross_cats_sorted":["cs.LG","math.PR"],"title_canon_sha256":"6964346d33f0a2b6a63a490694db633836c101f896e12ae2ab6fb9b3c71dc94a","abstract_canon_sha256":"3c6f5cc99edea3d29a8785fa71fdd65ff1e5265832c840c33f048360032618bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:58.569104Z","signature_b64":"nsTUf7JmjATrEMs066gkjU0yGGQlvp/19Yk9XgLSk3CnpkXcoOxxerr/2bmdA8MeYeaiH7uP2EnnvpIEWMwSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42a8d8579ef3ca03034b7ee232a934b4f1d7f90abf4476d67d6231cb372cefad","last_reissued_at":"2026-07-05T05:04:58.568642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:58.568642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Modeling with Denoising Auto-Encoders and Langevin Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Adam Block, Alexander Rakhlin, Youssef Mroueh","submitted_at":"2020-01-31T23:50:03Z","abstract_excerpt":"We study convergence of a generative modeling method that first estimates the score function of the distribution using Denoising Auto-Encoders (DAE) or Denoising Score Matching (DSM) and then employs Langevin diffusion for sampling. We show that both DAE and DSM provide estimates of the score of the Gaussian smoothed population density, allowing us to apply the machinery of Empirical Processes.\n  We overcome the challenge of relying only on $L^2$ bounds on the score estimation error and provide finite-sample bounds in the Wasserstein distance between the law of the population distribution and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.00107","kind":"arxiv","version":4},"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/2002.00107/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":"2002.00107","created_at":"2026-07-05T05:04:58.568700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.00107v4","created_at":"2026-07-05T05:04:58.568700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.00107","created_at":"2026-07-05T05:04:58.568700+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKUNQV466PFA","created_at":"2026-07-05T05:04:58.568700+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKUNQV466PFAGA2L","created_at":"2026-07-05T05:04:58.568700+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKUNQV46","created_at":"2026-07-05T05:04:58.568700+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25086","citing_title":"Training for the Model You Return: Improving Optimization for Iterate-Averaged Language Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23920","citing_title":"Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolate","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":247,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":247,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03360","citing_title":"Structured drift design for denoising diffusion models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25086","citing_title":"Training for the Model You Return: Improving Optimization for Iterate-Averaged Language Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2503.11615","citing_title":"From Score Matching to Diffusion: A Fine-Grained Error Analysis in the Gaussian Setting","ref_index":4,"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":2,"is_internal_anchor":false},{"citing_arxiv_id":"2603.20645","citing_title":"Diffusion Model for Manifold Data: Score Decomposition, Curvature, and Statistical Complexity","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13448","citing_title":"On the Limits of Latent Reuse in Diffusion Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00229","citing_title":"A unified perspective on fine-tuning and sampling with diffusion and flow models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07513","citing_title":"Tessellations of Semi-Discrete Flow Matching","ref_index":111,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IKUNQV466PFAGA2LP3RDFKJUWT","json":"https://pith.science/pith/IKUNQV466PFAGA2LP3RDFKJUWT.json","graph_json":"https://pith.science/api/pith-number/IKUNQV466PFAGA2LP3RDFKJUWT/graph.json","events_json":"https://pith.science/api/pith-number/IKUNQV466PFAGA2LP3RDFKJUWT/events.json","paper":"https://pith.science/paper/IKUNQV46"},"agent_actions":{"view_html":"https://pith.science/pith/IKUNQV466PFAGA2LP3RDFKJUWT","download_json":"https://pith.science/pith/IKUNQV466PFAGA2LP3RDFKJUWT.json","view_paper":"https://pith.science/paper/IKUNQV46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.00107&json=true","fetch_graph":"https://pith.science/api/pith-number/IKUNQV466PFAGA2LP3RDFKJUWT/graph.json","fetch_events":"https://pith.science/api/pith-number/IKUNQV466PFAGA2LP3RDFKJUWT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKUNQV466PFAGA2LP3RDFKJUWT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKUNQV466PFAGA2LP3RDFKJUWT/action/storage_attestation","attest_author":"https://pith.science/pith/IKUNQV466PFAGA2LP3RDFKJUWT/action/author_attestation","sign_citation":"https://pith.science/pith/IKUNQV466PFAGA2LP3RDFKJUWT/action/citation_signature","submit_replication":"https://pith.science/pith/IKUNQV466PFAGA2LP3RDFKJUWT/action/replication_record"}},"created_at":"2026-07-05T05:04:58.568700+00:00","updated_at":"2026-07-05T05:04:58.568700+00:00"}