{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WXLFLQ6PLUOLI2I2S3YE7QQSHJ","short_pith_number":"pith:WXLFLQ6P","schema_version":"1.0","canonical_sha256":"b5d655c3cf5d1cb4691a96f04fc2123a78f8afb419b7818d27e9f7f21590b7df","source":{"kind":"arxiv","id":"2402.05468","version":3},"attestation_state":"computed","paper":{"title":"Implicit Diffusion: Efficient Optimization through Stochastic Sampling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anna Korba, Arnaud Doucet, Courtney Paquette, Felipe Llinares-L\\'opez, Mathieu Blondel, Peter Bartlett, Pierre Marion, Quentin Berthet, Valentin De Bortoli","submitted_at":"2024-02-08T08:00:11Z","abstract_excerpt":"We present a new algorithm to optimize distributions defined implicitly by parameterized stochastic diffusions. Doing so allows us to modify the outcome distribution of sampling processes by optimizing over their parameters. We introduce a general framework for first-order optimization of these processes, that performs jointly, in a single loop, optimization and sampling steps. This approach is inspired by recent advances in bilevel optimization and automatic implicit differentiation, leveraging the point of view of sampling as optimization over the space of probability distributions. We provi"},"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":"2402.05468","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T08:00:11Z","cross_cats_sorted":[],"title_canon_sha256":"fdaab1af4bbfe6c3e69449c9d3d57387233a72c1f9babcd6479e80af84275960","abstract_canon_sha256":"62750c4e51dddb8b9b72f2879b433d30cd0268fbb55c692d3fc99e2d2a991b13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:04.753537Z","signature_b64":"YTNwP8CKYtKlyKRaUIa1yPNtZs9fFbm7pz5ii5QUCWtXrfGr3UNZmvhoxzqV3Gdt2XASBtEe18I9xUJw4SS0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5d655c3cf5d1cb4691a96f04fc2123a78f8afb419b7818d27e9f7f21590b7df","last_reissued_at":"2026-07-05T10:25:04.753022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:04.753022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Implicit Diffusion: Efficient Optimization through Stochastic Sampling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anna Korba, Arnaud Doucet, Courtney Paquette, Felipe Llinares-L\\'opez, Mathieu Blondel, Peter Bartlett, Pierre Marion, Quentin Berthet, Valentin De Bortoli","submitted_at":"2024-02-08T08:00:11Z","abstract_excerpt":"We present a new algorithm to optimize distributions defined implicitly by parameterized stochastic diffusions. Doing so allows us to modify the outcome distribution of sampling processes by optimizing over their parameters. We introduce a general framework for first-order optimization of these processes, that performs jointly, in a single loop, optimization and sampling steps. This approach is inspired by recent advances in bilevel optimization and automatic implicit differentiation, leveraging the point of view of sampling as optimization over the space of probability distributions. We provi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05468","kind":"arxiv","version":3},"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/2402.05468/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":"2402.05468","created_at":"2026-07-05T10:25:04.753082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05468v3","created_at":"2026-07-05T10:25:04.753082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05468","created_at":"2026-07-05T10:25:04.753082+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXLFLQ6PLUOL","created_at":"2026-07-05T10:25:04.753082+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXLFLQ6PLUOLI2I2","created_at":"2026-07-05T10:25:04.753082+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXLFLQ6P","created_at":"2026-07-05T10:25:04.753082+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08335","citing_title":"Bayesian Experimental Design via Score Matching","ref_index":173,"is_internal_anchor":true},{"citing_arxiv_id":"2606.05649","citing_title":"Diff2SP: Diffusion Models for Correlated Scenario Generation in Stochastic Programming","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WXLFLQ6PLUOLI2I2S3YE7QQSHJ","json":"https://pith.science/pith/WXLFLQ6PLUOLI2I2S3YE7QQSHJ.json","graph_json":"https://pith.science/api/pith-number/WXLFLQ6PLUOLI2I2S3YE7QQSHJ/graph.json","events_json":"https://pith.science/api/pith-number/WXLFLQ6PLUOLI2I2S3YE7QQSHJ/events.json","paper":"https://pith.science/paper/WXLFLQ6P"},"agent_actions":{"view_html":"https://pith.science/pith/WXLFLQ6PLUOLI2I2S3YE7QQSHJ","download_json":"https://pith.science/pith/WXLFLQ6PLUOLI2I2S3YE7QQSHJ.json","view_paper":"https://pith.science/paper/WXLFLQ6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05468&json=true","fetch_graph":"https://pith.science/api/pith-number/WXLFLQ6PLUOLI2I2S3YE7QQSHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WXLFLQ6PLUOLI2I2S3YE7QQSHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXLFLQ6PLUOLI2I2S3YE7QQSHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXLFLQ6PLUOLI2I2S3YE7QQSHJ/action/storage_attestation","attest_author":"https://pith.science/pith/WXLFLQ6PLUOLI2I2S3YE7QQSHJ/action/author_attestation","sign_citation":"https://pith.science/pith/WXLFLQ6PLUOLI2I2S3YE7QQSHJ/action/citation_signature","submit_replication":"https://pith.science/pith/WXLFLQ6PLUOLI2I2S3YE7QQSHJ/action/replication_record"}},"created_at":"2026-07-05T10:25:04.753082+00:00","updated_at":"2026-07-05T10:25:04.753082+00:00"}