{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PBMBGERUJ635MJ7J5BPHJJVCU4","short_pith_number":"pith:PBMBGERU","schema_version":"1.0","canonical_sha256":"78581312344fb7d627e9e85e74a6a2a734714d068814bc527a056fd76931c393","source":{"kind":"arxiv","id":"1708.01955","version":3},"attestation_state":"computed","paper":{"title":"Wasserstein Dictionary Learning: Optimal Transport-based unsupervised non-linear dictionary learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","math.OC"],"primary_cat":"stat.ML","authors_text":"David Coeurjolly, Fred Maurice Ngol\\`e Mboula, Gabriel Peyr\\'e, Jean-Luc Starck, Marco Cuturi, Matthieu Heitz, Morgan A. Schmitz, Nicolas Bonneel","submitted_at":"2017-08-07T01:00:40Z","abstract_excerpt":"This paper introduces a new nonlinear dictionary learning method for histograms in the probability simplex. The method leverages optimal transport theory, in the sense that our aim is to reconstruct histograms using so-called displacement interpolations (a.k.a. Wasserstein barycenters) between dictionary atoms; such atoms are themselves synthetic histograms in the probability simplex. Our method simultaneously estimates such atoms, and, for each datapoint, the vector of weights that can optimally reconstruct it as an optimal transport barycenter of such atoms. Our method is computationally tra"},"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":"1708.01955","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-08-07T01:00:40Z","cross_cats_sorted":["cs.GR","math.OC"],"title_canon_sha256":"8c5a1263edf38510c873de335e0984d4205b915e6f58f8def26d3726d992b350","abstract_canon_sha256":"6e3b025b3dba1146df266d5061aa0e3a6cfb2d16a71ea18e4d809602690633bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:56.324928Z","signature_b64":"Gfwh1ZH6kuKjxmj4jLivAWXW8gLIE69iBZKvrz8ccFDKEAgmRhh3UWgL572igMGYjzTaVGT4vLwnSmDbjAa1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78581312344fb7d627e9e85e74a6a2a734714d068814bc527a056fd76931c393","last_reissued_at":"2026-05-18T00:20:56.324304Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:56.324304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wasserstein Dictionary Learning: Optimal Transport-based unsupervised non-linear dictionary learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","math.OC"],"primary_cat":"stat.ML","authors_text":"David Coeurjolly, Fred Maurice Ngol\\`e Mboula, Gabriel Peyr\\'e, Jean-Luc Starck, Marco Cuturi, Matthieu Heitz, Morgan A. Schmitz, Nicolas Bonneel","submitted_at":"2017-08-07T01:00:40Z","abstract_excerpt":"This paper introduces a new nonlinear dictionary learning method for histograms in the probability simplex. The method leverages optimal transport theory, in the sense that our aim is to reconstruct histograms using so-called displacement interpolations (a.k.a. Wasserstein barycenters) between dictionary atoms; such atoms are themselves synthetic histograms in the probability simplex. Our method simultaneously estimates such atoms, and, for each datapoint, the vector of weights that can optimally reconstruct it as an optimal transport barycenter of such atoms. Our method is computationally tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01955","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":""},"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":"1708.01955","created_at":"2026-05-18T00:20:56.324419+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.01955v3","created_at":"2026-05-18T00:20:56.324419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01955","created_at":"2026-05-18T00:20:56.324419+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBMBGERUJ635","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBMBGERUJ635MJ7J","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBMBGERU","created_at":"2026-05-18T12:31:37.085036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PBMBGERUJ635MJ7J5BPHJJVCU4","json":"https://pith.science/pith/PBMBGERUJ635MJ7J5BPHJJVCU4.json","graph_json":"https://pith.science/api/pith-number/PBMBGERUJ635MJ7J5BPHJJVCU4/graph.json","events_json":"https://pith.science/api/pith-number/PBMBGERUJ635MJ7J5BPHJJVCU4/events.json","paper":"https://pith.science/paper/PBMBGERU"},"agent_actions":{"view_html":"https://pith.science/pith/PBMBGERUJ635MJ7J5BPHJJVCU4","download_json":"https://pith.science/pith/PBMBGERUJ635MJ7J5BPHJJVCU4.json","view_paper":"https://pith.science/paper/PBMBGERU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.01955&json=true","fetch_graph":"https://pith.science/api/pith-number/PBMBGERUJ635MJ7J5BPHJJVCU4/graph.json","fetch_events":"https://pith.science/api/pith-number/PBMBGERUJ635MJ7J5BPHJJVCU4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBMBGERUJ635MJ7J5BPHJJVCU4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBMBGERUJ635MJ7J5BPHJJVCU4/action/storage_attestation","attest_author":"https://pith.science/pith/PBMBGERUJ635MJ7J5BPHJJVCU4/action/author_attestation","sign_citation":"https://pith.science/pith/PBMBGERUJ635MJ7J5BPHJJVCU4/action/citation_signature","submit_replication":"https://pith.science/pith/PBMBGERUJ635MJ7J5BPHJJVCU4/action/replication_record"}},"created_at":"2026-05-18T00:20:56.324419+00:00","updated_at":"2026-05-18T00:20:56.324419+00:00"}