{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GH75IQCB2PFACRBK2QZBNDMV4X","short_pith_number":"pith:GH75IQCB","schema_version":"1.0","canonical_sha256":"31ffd44041d3ca01442ad432168d95e5e52323eb211c62e73b615ed94821f05f","source":{"kind":"arxiv","id":"2106.06338","version":3},"attestation_state":"computed","paper":{"title":"Understanding approximate and unrolled dictionary learning for pattern recovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Beno\\^it Mal\\'ezieux, Matthieu Kowalski, Thomas Moreau","submitted_at":"2021-06-11T12:21:26Z","abstract_excerpt":"Dictionary learning consists of finding a sparse representation from noisy data and is a common way to encode data-driven prior knowledge on signals. Alternating minimization (AM) is standard for the underlying optimization, where gradient descent steps alternate with sparse coding procedures. The major drawback of this method is its prohibitive computational cost, making it unpractical on large real-world data sets. This work studies an approximate formulation of dictionary learning based on unrolling and compares it to alternating minimization to find the best trade-off between speed and pre"},"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":"2106.06338","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-11T12:21:26Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"b5583a157d3640ff5c8a118be000d2ac1ce59fc5ee54ba615ed8584ef8af1db2","abstract_canon_sha256":"4e54463613b3a364e3717c806c9c2dd703ff689c791a8c6f4d8e383302172707"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:41.513455Z","signature_b64":"HinFIObBN1bl2lDl3RF51L0JHsqoohmlGJ3a35CLFuJ3FpFR3G2enL2sIN+7uLSCVClAzo8QTCfFNmbWsFQNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31ffd44041d3ca01442ad432168d95e5e52323eb211c62e73b615ed94821f05f","last_reissued_at":"2026-07-05T03:54:41.512985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:41.512985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding approximate and unrolled dictionary learning for pattern recovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Beno\\^it Mal\\'ezieux, Matthieu Kowalski, Thomas Moreau","submitted_at":"2021-06-11T12:21:26Z","abstract_excerpt":"Dictionary learning consists of finding a sparse representation from noisy data and is a common way to encode data-driven prior knowledge on signals. Alternating minimization (AM) is standard for the underlying optimization, where gradient descent steps alternate with sparse coding procedures. The major drawback of this method is its prohibitive computational cost, making it unpractical on large real-world data sets. This work studies an approximate formulation of dictionary learning based on unrolling and compares it to alternating minimization to find the best trade-off between speed and pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06338","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/2106.06338/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":"2106.06338","created_at":"2026-07-05T03:54:41.513044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06338v3","created_at":"2026-07-05T03:54:41.513044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06338","created_at":"2026-07-05T03:54:41.513044+00:00"},{"alias_kind":"pith_short_12","alias_value":"GH75IQCB2PFA","created_at":"2026-07-05T03:54:41.513044+00:00"},{"alias_kind":"pith_short_16","alias_value":"GH75IQCB2PFACRBK","created_at":"2026-07-05T03:54:41.513044+00:00"},{"alias_kind":"pith_short_8","alias_value":"GH75IQCB","created_at":"2026-07-05T03:54:41.513044+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19205","citing_title":"Discovering a well-conditioned analytic continuation problem via dictionary learning","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GH75IQCB2PFACRBK2QZBNDMV4X","json":"https://pith.science/pith/GH75IQCB2PFACRBK2QZBNDMV4X.json","graph_json":"https://pith.science/api/pith-number/GH75IQCB2PFACRBK2QZBNDMV4X/graph.json","events_json":"https://pith.science/api/pith-number/GH75IQCB2PFACRBK2QZBNDMV4X/events.json","paper":"https://pith.science/paper/GH75IQCB"},"agent_actions":{"view_html":"https://pith.science/pith/GH75IQCB2PFACRBK2QZBNDMV4X","download_json":"https://pith.science/pith/GH75IQCB2PFACRBK2QZBNDMV4X.json","view_paper":"https://pith.science/paper/GH75IQCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06338&json=true","fetch_graph":"https://pith.science/api/pith-number/GH75IQCB2PFACRBK2QZBNDMV4X/graph.json","fetch_events":"https://pith.science/api/pith-number/GH75IQCB2PFACRBK2QZBNDMV4X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GH75IQCB2PFACRBK2QZBNDMV4X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GH75IQCB2PFACRBK2QZBNDMV4X/action/storage_attestation","attest_author":"https://pith.science/pith/GH75IQCB2PFACRBK2QZBNDMV4X/action/author_attestation","sign_citation":"https://pith.science/pith/GH75IQCB2PFACRBK2QZBNDMV4X/action/citation_signature","submit_replication":"https://pith.science/pith/GH75IQCB2PFACRBK2QZBNDMV4X/action/replication_record"}},"created_at":"2026-07-05T03:54:41.513044+00:00","updated_at":"2026-07-05T03:54:41.513044+00:00"}