{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GUXAHNRZC2OWTK3HSKG6ABAVFU","short_pith_number":"pith:GUXAHNRZ","schema_version":"1.0","canonical_sha256":"352e03b639169d69ab67928de004152d1823fe0a764ca632059a58287f5a79de","source":{"kind":"arxiv","id":"2106.00774","version":3},"attestation_state":"computed","paper":{"title":"Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"stat.ML","authors_text":"David Alvarez-Melis, Yair Schiff, Youssef Mroueh","submitted_at":"2021-06-01T20:13:18Z","abstract_excerpt":"Gradient flows are a powerful tool for optimizing functionals in general metric spaces, including the space of probabilities endowed with the Wasserstein metric. A typical approach to solving this optimization problem relies on its connection to the dynamic formulation of optimal transport and the celebrated Jordan-Kinderlehrer-Otto (JKO) scheme. However, this formulation involves optimization over convex functions, which is challenging, especially in high dimensions. In this work, we propose an approach that relies on the recently introduced input-convex neural networks (ICNN) to parametrize "},"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":"2106.00774","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-01T20:13:18Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"title_canon_sha256":"8c8383d9895a5e4b2981244c03f27309971543354b38d656f1bfcf75721f1fd0","abstract_canon_sha256":"2cba48138370a04446b48252dc58fa8d4563561906d7b93d59f11c40d5078571"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:37.999632Z","signature_b64":"05ELrnajXUP0wZCsHyZT43pwNzlsyZ7B52AGDjHSzeQBw8qGXTIWjafqRoNLGrOuG2rfUTa2ncTz2pE6ILNRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"352e03b639169d69ab67928de004152d1823fe0a764ca632059a58287f5a79de","last_reissued_at":"2026-07-05T03:36:37.999152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:37.999152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"stat.ML","authors_text":"David Alvarez-Melis, Yair Schiff, Youssef Mroueh","submitted_at":"2021-06-01T20:13:18Z","abstract_excerpt":"Gradient flows are a powerful tool for optimizing functionals in general metric spaces, including the space of probabilities endowed with the Wasserstein metric. A typical approach to solving this optimization problem relies on its connection to the dynamic formulation of optimal transport and the celebrated Jordan-Kinderlehrer-Otto (JKO) scheme. However, this formulation involves optimization over convex functions, which is challenging, especially in high dimensions. In this work, we propose an approach that relies on the recently introduced input-convex neural networks (ICNN) to parametrize "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00774","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/2106.00774/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":"2106.00774","created_at":"2026-07-05T03:36:37.999209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.00774v3","created_at":"2026-07-05T03:36:37.999209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00774","created_at":"2026-07-05T03:36:37.999209+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUXAHNRZC2OW","created_at":"2026-07-05T03:36:37.999209+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUXAHNRZC2OWTK3H","created_at":"2026-07-05T03:36:37.999209+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUXAHNRZ","created_at":"2026-07-05T03:36:37.999209+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24106","citing_title":"Flexible and Stable Dynamics Discovery with Onsager's Variational Principle","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10792","citing_title":"Implicit Neural Optimal Transport via Fixed-Point Optimization","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10237","citing_title":"Minimalist Genetic Programming","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23778","citing_title":"The physics of AI weather models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2509.04477","citing_title":"Universal Representation of Generalized Convex Functions and their Gradients","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10792","citing_title":"Implicit Neural Optimal Transport via Fixed-Point Optimization","ref_index":197,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GUXAHNRZC2OWTK3HSKG6ABAVFU","json":"https://pith.science/pith/GUXAHNRZC2OWTK3HSKG6ABAVFU.json","graph_json":"https://pith.science/api/pith-number/GUXAHNRZC2OWTK3HSKG6ABAVFU/graph.json","events_json":"https://pith.science/api/pith-number/GUXAHNRZC2OWTK3HSKG6ABAVFU/events.json","paper":"https://pith.science/paper/GUXAHNRZ"},"agent_actions":{"view_html":"https://pith.science/pith/GUXAHNRZC2OWTK3HSKG6ABAVFU","download_json":"https://pith.science/pith/GUXAHNRZC2OWTK3HSKG6ABAVFU.json","view_paper":"https://pith.science/paper/GUXAHNRZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.00774&json=true","fetch_graph":"https://pith.science/api/pith-number/GUXAHNRZC2OWTK3HSKG6ABAVFU/graph.json","fetch_events":"https://pith.science/api/pith-number/GUXAHNRZC2OWTK3HSKG6ABAVFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUXAHNRZC2OWTK3HSKG6ABAVFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUXAHNRZC2OWTK3HSKG6ABAVFU/action/storage_attestation","attest_author":"https://pith.science/pith/GUXAHNRZC2OWTK3HSKG6ABAVFU/action/author_attestation","sign_citation":"https://pith.science/pith/GUXAHNRZC2OWTK3HSKG6ABAVFU/action/citation_signature","submit_replication":"https://pith.science/pith/GUXAHNRZC2OWTK3HSKG6ABAVFU/action/replication_record"}},"created_at":"2026-07-05T03:36:37.999209+00:00","updated_at":"2026-07-05T03:36:37.999209+00:00"}