{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:TZ25N4HDIUOITAEX5H7TOQGX5Y","short_pith_number":"pith:TZ25N4HD","schema_version":"1.0","canonical_sha256":"9e75d6f0e3451c898097e9ff3740d7ee137f07c6283e2d26a2f7d04b7dda2271","source":{"kind":"arxiv","id":"1512.04754","version":1},"attestation_state":"computed","paper":{"title":"Learning optimal nonlinearities for iterative thresholding algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hassan Mansour, Ulugbek S. Kamilov","submitted_at":"2015-12-15T12:20:17Z","abstract_excerpt":"Iterative shrinkage/thresholding algorithm (ISTA) is a well-studied method for finding sparse solutions to ill-posed inverse problems. In this letter, we present a data-driven scheme for learning optimal thresholding functions for ISTA. The proposed scheme is obtained by relating iterations of ISTA to layers of a simple deep neural network (DNN) and developing a corresponding error backpropagation algorithm that allows to fine-tune the thresholding functions. Simulations on sparse statistical signals illustrate potential gains in estimation quality due to the proposed data adaptive ISTA."},"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":"1512.04754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-15T12:20:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dcf634f7571307cf44c3e18efe53af26337aa9656c9a86f976692480b84d9153","abstract_canon_sha256":"fba6ec7a268e786c623bb37c42284861406e718e849bffcde0dd5f588cc18420"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:15:43.448616Z","signature_b64":"z2Rw936qnXK/dWNy0JfIMjS1FkqGPm+xGCjf5EDsnItyQSw5iCpzLhoImaJ/jKWVoF1G7EnAqFJqa2R3xlyEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e75d6f0e3451c898097e9ff3740d7ee137f07c6283e2d26a2f7d04b7dda2271","last_reissued_at":"2026-05-18T01:15:43.448127Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:15:43.448127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning optimal nonlinearities for iterative thresholding algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hassan Mansour, Ulugbek S. Kamilov","submitted_at":"2015-12-15T12:20:17Z","abstract_excerpt":"Iterative shrinkage/thresholding algorithm (ISTA) is a well-studied method for finding sparse solutions to ill-posed inverse problems. In this letter, we present a data-driven scheme for learning optimal thresholding functions for ISTA. The proposed scheme is obtained by relating iterations of ISTA to layers of a simple deep neural network (DNN) and developing a corresponding error backpropagation algorithm that allows to fine-tune the thresholding functions. Simulations on sparse statistical signals illustrate potential gains in estimation quality due to the proposed data adaptive ISTA."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.04754","kind":"arxiv","version":1},"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":"1512.04754","created_at":"2026-05-18T01:15:43.448207+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.04754v1","created_at":"2026-05-18T01:15:43.448207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.04754","created_at":"2026-05-18T01:15:43.448207+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZ25N4HDIUOI","created_at":"2026-05-18T12:29:44.643036+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZ25N4HDIUOITAEX","created_at":"2026-05-18T12:29:44.643036+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZ25N4HD","created_at":"2026-05-18T12:29:44.643036+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/TZ25N4HDIUOITAEX5H7TOQGX5Y","json":"https://pith.science/pith/TZ25N4HDIUOITAEX5H7TOQGX5Y.json","graph_json":"https://pith.science/api/pith-number/TZ25N4HDIUOITAEX5H7TOQGX5Y/graph.json","events_json":"https://pith.science/api/pith-number/TZ25N4HDIUOITAEX5H7TOQGX5Y/events.json","paper":"https://pith.science/paper/TZ25N4HD"},"agent_actions":{"view_html":"https://pith.science/pith/TZ25N4HDIUOITAEX5H7TOQGX5Y","download_json":"https://pith.science/pith/TZ25N4HDIUOITAEX5H7TOQGX5Y.json","view_paper":"https://pith.science/paper/TZ25N4HD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.04754&json=true","fetch_graph":"https://pith.science/api/pith-number/TZ25N4HDIUOITAEX5H7TOQGX5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/TZ25N4HDIUOITAEX5H7TOQGX5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZ25N4HDIUOITAEX5H7TOQGX5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZ25N4HDIUOITAEX5H7TOQGX5Y/action/storage_attestation","attest_author":"https://pith.science/pith/TZ25N4HDIUOITAEX5H7TOQGX5Y/action/author_attestation","sign_citation":"https://pith.science/pith/TZ25N4HDIUOITAEX5H7TOQGX5Y/action/citation_signature","submit_replication":"https://pith.science/pith/TZ25N4HDIUOITAEX5H7TOQGX5Y/action/replication_record"}},"created_at":"2026-05-18T01:15:43.448207+00:00","updated_at":"2026-05-18T01:15:43.448207+00:00"}