{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:A7GJKOKVC4456ANG3QIDXGJW47","short_pith_number":"pith:A7GJKOKV","schema_version":"1.0","canonical_sha256":"07cc9539551739df01a6dc103b9936e7d489da3eda8e7b7f4a81fc5004129bf4","source":{"kind":"arxiv","id":"2110.10972","version":3},"attestation_state":"computed","paper":{"title":"Efficient Gradient Flows in Sliced-Wasserstein Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cl\\'ement Bonet, Fran\\c{c}ois Septier, Lucas Drumetz, Nicolas Courty","submitted_at":"2021-10-21T08:34:26Z","abstract_excerpt":"Minimizing functionals in the space of probability distributions can be done with Wasserstein gradient flows. To solve them numerically, a possible approach is to rely on the Jordan-Kinderlehrer-Otto (JKO) scheme which is analogous to the proximal scheme in Euclidean spaces. However, it requires solving a nested optimization problem at each iteration, and is known for its computational challenges, especially in high dimension. To alleviate it, very recent works propose to approximate the JKO scheme leveraging Brenier's theorem, and using gradients of Input Convex Neural Networks to parameteriz"},"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":"2110.10972","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-21T08:34:26Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"d14d451745c583786bf112053894bf7fdb8a266958f7ce5dea15dd40966d8d7c","abstract_canon_sha256":"31b9667624391979ae8a4a259891cf0fc729e016fc6cab3a97950cf9842d0698"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:57.806966Z","signature_b64":"cvnCKli12mz3J1zDgmqvmMZO2H1/c1uhWZA2naG9PMjUk2RYrGkTPKBsLgVcTEG7rkStP8OqwX7xRmBNR7MYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07cc9539551739df01a6dc103b9936e7d489da3eda8e7b7f4a81fc5004129bf4","last_reissued_at":"2026-07-05T05:15:57.806568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:57.806568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Gradient Flows in Sliced-Wasserstein Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cl\\'ement Bonet, Fran\\c{c}ois Septier, Lucas Drumetz, Nicolas Courty","submitted_at":"2021-10-21T08:34:26Z","abstract_excerpt":"Minimizing functionals in the space of probability distributions can be done with Wasserstein gradient flows. To solve them numerically, a possible approach is to rely on the Jordan-Kinderlehrer-Otto (JKO) scheme which is analogous to the proximal scheme in Euclidean spaces. However, it requires solving a nested optimization problem at each iteration, and is known for its computational challenges, especially in high dimension. To alleviate it, very recent works propose to approximate the JKO scheme leveraging Brenier's theorem, and using gradients of Input Convex Neural Networks to parameteriz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10972","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/2110.10972/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":"2110.10972","created_at":"2026-07-05T05:15:57.806623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.10972v3","created_at":"2026-07-05T05:15:57.806623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10972","created_at":"2026-07-05T05:15:57.806623+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7GJKOKVC445","created_at":"2026-07-05T05:15:57.806623+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7GJKOKVC4456ANG","created_at":"2026-07-05T05:15:57.806623+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7GJKOKV","created_at":"2026-07-05T05:15:57.806623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10651","citing_title":"Understanding Learning with Sliced-Wasserstein Requires Rethinking Informative Slices","ref_index":2018,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A7GJKOKVC4456ANG3QIDXGJW47","json":"https://pith.science/pith/A7GJKOKVC4456ANG3QIDXGJW47.json","graph_json":"https://pith.science/api/pith-number/A7GJKOKVC4456ANG3QIDXGJW47/graph.json","events_json":"https://pith.science/api/pith-number/A7GJKOKVC4456ANG3QIDXGJW47/events.json","paper":"https://pith.science/paper/A7GJKOKV"},"agent_actions":{"view_html":"https://pith.science/pith/A7GJKOKVC4456ANG3QIDXGJW47","download_json":"https://pith.science/pith/A7GJKOKVC4456ANG3QIDXGJW47.json","view_paper":"https://pith.science/paper/A7GJKOKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.10972&json=true","fetch_graph":"https://pith.science/api/pith-number/A7GJKOKVC4456ANG3QIDXGJW47/graph.json","fetch_events":"https://pith.science/api/pith-number/A7GJKOKVC4456ANG3QIDXGJW47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7GJKOKVC4456ANG3QIDXGJW47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7GJKOKVC4456ANG3QIDXGJW47/action/storage_attestation","attest_author":"https://pith.science/pith/A7GJKOKVC4456ANG3QIDXGJW47/action/author_attestation","sign_citation":"https://pith.science/pith/A7GJKOKVC4456ANG3QIDXGJW47/action/citation_signature","submit_replication":"https://pith.science/pith/A7GJKOKVC4456ANG3QIDXGJW47/action/replication_record"}},"created_at":"2026-07-05T05:15:57.806623+00:00","updated_at":"2026-07-05T05:15:57.806623+00:00"}