{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PR35ADAMMG37P5FSIYPUWT3FJI","short_pith_number":"pith:PR35ADAM","schema_version":"1.0","canonical_sha256":"7c77d00c0c61b7f7f4b2461f4b4f654a04b4cb8c28ba5b9fc66e913b909042ab","source":{"kind":"arxiv","id":"1705.04193","version":2},"attestation_state":"computed","paper":{"title":"Nonnegative Matrix Factorization with Transform Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"C\\'edric F\\'evotte, Dylan Fagot, Herwig Wendt","submitted_at":"2017-05-11T14:12:23Z","abstract_excerpt":"Traditional NMF-based signal decomposition relies on the factorization of spectral data, which is typically computed by means of short-time frequency transform. In this paper we propose to relax the choice of a pre-fixed transform and learn a short-time orthogonal transform together with the factorization. To this end, we formulate a regularized optimization problem reminiscent of conventional NMF, yet with the transform as additional unknown parameters, and design a novel block-descent algorithm enabling to find stationary points of this objective function. The proposed joint transform learni"},"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":"1705.04193","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-11T14:12:23Z","cross_cats_sorted":[],"title_canon_sha256":"001828d1da4fa92fee93762b6c4b9aa002e6fb80bb2e77c61e9ec7267eeb4250","abstract_canon_sha256":"9684752c2aee3d6632bda27d3f250e28b42cc09545470601f3b4a796ec010ad6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:57.382540Z","signature_b64":"0Xp7HiwD1yYCG1t1Mzcg5aHdSR+VC9TFgl4bo8zJuNtwkhucJoSYh26SoDG7OCWUgwpLxrc5nlFZYWpW/pvmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c77d00c0c61b7f7f4b2461f4b4f654a04b4cb8c28ba5b9fc66e913b909042ab","last_reissued_at":"2026-05-18T00:27:57.381921Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:57.381921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nonnegative Matrix Factorization with Transform Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"C\\'edric F\\'evotte, Dylan Fagot, Herwig Wendt","submitted_at":"2017-05-11T14:12:23Z","abstract_excerpt":"Traditional NMF-based signal decomposition relies on the factorization of spectral data, which is typically computed by means of short-time frequency transform. In this paper we propose to relax the choice of a pre-fixed transform and learn a short-time orthogonal transform together with the factorization. To this end, we formulate a regularized optimization problem reminiscent of conventional NMF, yet with the transform as additional unknown parameters, and design a novel block-descent algorithm enabling to find stationary points of this objective function. The proposed joint transform learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.04193","kind":"arxiv","version":2},"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":"1705.04193","created_at":"2026-05-18T00:27:57.382015+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.04193v2","created_at":"2026-05-18T00:27:57.382015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.04193","created_at":"2026-05-18T00:27:57.382015+00:00"},{"alias_kind":"pith_short_12","alias_value":"PR35ADAMMG37","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PR35ADAMMG37P5FS","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PR35ADAM","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/PR35ADAMMG37P5FSIYPUWT3FJI","json":"https://pith.science/pith/PR35ADAMMG37P5FSIYPUWT3FJI.json","graph_json":"https://pith.science/api/pith-number/PR35ADAMMG37P5FSIYPUWT3FJI/graph.json","events_json":"https://pith.science/api/pith-number/PR35ADAMMG37P5FSIYPUWT3FJI/events.json","paper":"https://pith.science/paper/PR35ADAM"},"agent_actions":{"view_html":"https://pith.science/pith/PR35ADAMMG37P5FSIYPUWT3FJI","download_json":"https://pith.science/pith/PR35ADAMMG37P5FSIYPUWT3FJI.json","view_paper":"https://pith.science/paper/PR35ADAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.04193&json=true","fetch_graph":"https://pith.science/api/pith-number/PR35ADAMMG37P5FSIYPUWT3FJI/graph.json","fetch_events":"https://pith.science/api/pith-number/PR35ADAMMG37P5FSIYPUWT3FJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PR35ADAMMG37P5FSIYPUWT3FJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PR35ADAMMG37P5FSIYPUWT3FJI/action/storage_attestation","attest_author":"https://pith.science/pith/PR35ADAMMG37P5FSIYPUWT3FJI/action/author_attestation","sign_citation":"https://pith.science/pith/PR35ADAMMG37P5FSIYPUWT3FJI/action/citation_signature","submit_replication":"https://pith.science/pith/PR35ADAMMG37P5FSIYPUWT3FJI/action/replication_record"}},"created_at":"2026-05-18T00:27:57.382015+00:00","updated_at":"2026-05-18T00:27:57.382015+00:00"}