{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ACDWS7VUHZ34AOEPVUVIR3DRZ2","short_pith_number":"pith:ACDWS7VU","schema_version":"1.0","canonical_sha256":"0087697eb43e77c0388fad2a88ec71ceba90770a042377baaf7a0eff241261b1","source":{"kind":"arxiv","id":"1703.00119","version":2},"attestation_state":"computed","paper":{"title":"Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Dimitris N. Metaxas, Lezi Wang, Qingshan Liu, Xiao-Tong Yuan","submitted_at":"2017-03-01T03:30:47Z","abstract_excerpt":"Iterative Hard Thresholding (IHT) is a class of projected gradient descent methods for optimizing sparsity-constrained minimization models, with the best known efficiency and scalability in practice. As far as we know, the existing IHT-style methods are designed for sparse minimization in primal form. It remains open to explore duality theory and algorithms in such a non-convex and NP-hard problem setting. In this paper, we bridge this gap by establishing a duality theory for sparsity-constrained minimization with $\\ell_2$-regularized loss function and proposing an IHT-style algorithm for dual"},"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":"1703.00119","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-01T03:30:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7ff3d9a1546e941d315cd49713515f0f4a020f362ab25a59fd64141d38d35a4f","abstract_canon_sha256":"6097e6102baf21177db9545932602963d75fb5671a7fa9be89db079ee3852281"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:57.880938Z","signature_b64":"wkzgtGP/y/vY+/THNvJCS5tEmT8Hq2BKXf5iOU+pvHWqU9oCZKhIXxoU7K8eDvLoFJnQa2nZqxakvlZoKoBSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0087697eb43e77c0388fad2a88ec71ceba90770a042377baaf7a0eff241261b1","last_reissued_at":"2026-05-18T00:41:57.880371Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:57.880371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Dimitris N. Metaxas, Lezi Wang, Qingshan Liu, Xiao-Tong Yuan","submitted_at":"2017-03-01T03:30:47Z","abstract_excerpt":"Iterative Hard Thresholding (IHT) is a class of projected gradient descent methods for optimizing sparsity-constrained minimization models, with the best known efficiency and scalability in practice. As far as we know, the existing IHT-style methods are designed for sparse minimization in primal form. It remains open to explore duality theory and algorithms in such a non-convex and NP-hard problem setting. In this paper, we bridge this gap by establishing a duality theory for sparsity-constrained minimization with $\\ell_2$-regularized loss function and proposing an IHT-style algorithm for dual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00119","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":"1703.00119","created_at":"2026-05-18T00:41:57.880457+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.00119v2","created_at":"2026-05-18T00:41:57.880457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00119","created_at":"2026-05-18T00:41:57.880457+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACDWS7VUHZ34","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACDWS7VUHZ34AOEP","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACDWS7VU","created_at":"2026-05-18T12:31:05.417338+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/ACDWS7VUHZ34AOEPVUVIR3DRZ2","json":"https://pith.science/pith/ACDWS7VUHZ34AOEPVUVIR3DRZ2.json","graph_json":"https://pith.science/api/pith-number/ACDWS7VUHZ34AOEPVUVIR3DRZ2/graph.json","events_json":"https://pith.science/api/pith-number/ACDWS7VUHZ34AOEPVUVIR3DRZ2/events.json","paper":"https://pith.science/paper/ACDWS7VU"},"agent_actions":{"view_html":"https://pith.science/pith/ACDWS7VUHZ34AOEPVUVIR3DRZ2","download_json":"https://pith.science/pith/ACDWS7VUHZ34AOEPVUVIR3DRZ2.json","view_paper":"https://pith.science/paper/ACDWS7VU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.00119&json=true","fetch_graph":"https://pith.science/api/pith-number/ACDWS7VUHZ34AOEPVUVIR3DRZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/ACDWS7VUHZ34AOEPVUVIR3DRZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACDWS7VUHZ34AOEPVUVIR3DRZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACDWS7VUHZ34AOEPVUVIR3DRZ2/action/storage_attestation","attest_author":"https://pith.science/pith/ACDWS7VUHZ34AOEPVUVIR3DRZ2/action/author_attestation","sign_citation":"https://pith.science/pith/ACDWS7VUHZ34AOEPVUVIR3DRZ2/action/citation_signature","submit_replication":"https://pith.science/pith/ACDWS7VUHZ34AOEPVUVIR3DRZ2/action/replication_record"}},"created_at":"2026-05-18T00:41:57.880457+00:00","updated_at":"2026-05-18T00:41:57.880457+00:00"}