{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:WAL24DRKKLTJT4CO7BMGDPOL4S","short_pith_number":"pith:WAL24DRK","schema_version":"1.0","canonical_sha256":"b017ae0e2a52e699f04ef85861bdcbe4ba0b3eebc47409a8f25026a3b002d2f3","source":{"kind":"arxiv","id":"1305.2436","version":2},"attestation_state":"computed","paper":{"title":"Regularized M-estimators with nonconvexity: Statistical and algorithmic theory for local optima","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Martin J. Wainwright, Po-Ling Loh","submitted_at":"2013-05-10T20:46:41Z","abstract_excerpt":"We provide novel theoretical results regarding local optima of regularized $M$-estimators, allowing for nonconvexity in both loss and penalty functions. Under restricted strong convexity on the loss and suitable regularity conditions on the penalty, we prove that \\emph{any stationary point} of the composite objective function will lie within statistical precision of the underlying parameter vector. Our theory covers many nonconvex objective functions of interest, including the corrected Lasso for errors-in-variables linear models; regression for generalized linear models with nonconvex penalti"},"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":"1305.2436","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2013-05-10T20:46:41Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML","stat.TH"],"title_canon_sha256":"2748f2b3d41acb54329601b85909ec773eedf13804063ece6863e9ec4a53541d","abstract_canon_sha256":"11dbbdb5741bb1df9c9195b36d2d822fbcbd9f9540f4aff9ddd97b4101596cba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:30:15.917336Z","signature_b64":"ea0KfNItNZ4Xa/5zvUsS9kRQioOS3NeVfGe3EiIAFHz7WnxH5/WH1qA/vErI+asl31p0TSSmmhV3S3pDR5YcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b017ae0e2a52e699f04ef85861bdcbe4ba0b3eebc47409a8f25026a3b002d2f3","last_reissued_at":"2026-05-18T02:30:15.916886Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:30:15.916886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regularized M-estimators with nonconvexity: Statistical and algorithmic theory for local optima","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Martin J. Wainwright, Po-Ling Loh","submitted_at":"2013-05-10T20:46:41Z","abstract_excerpt":"We provide novel theoretical results regarding local optima of regularized $M$-estimators, allowing for nonconvexity in both loss and penalty functions. Under restricted strong convexity on the loss and suitable regularity conditions on the penalty, we prove that \\emph{any stationary point} of the composite objective function will lie within statistical precision of the underlying parameter vector. Our theory covers many nonconvex objective functions of interest, including the corrected Lasso for errors-in-variables linear models; regression for generalized linear models with nonconvex penalti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1305.2436","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":"1305.2436","created_at":"2026-05-18T02:30:15.916952+00:00"},{"alias_kind":"arxiv_version","alias_value":"1305.2436v2","created_at":"2026-05-18T02:30:15.916952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1305.2436","created_at":"2026-05-18T02:30:15.916952+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAL24DRKKLTJ","created_at":"2026-05-18T12:28:04.890932+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAL24DRKKLTJT4CO","created_at":"2026-05-18T12:28:04.890932+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAL24DRK","created_at":"2026-05-18T12:28:04.890932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10649","citing_title":"Deep Loss Convexification for Learning Iterative Models","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WAL24DRKKLTJT4CO7BMGDPOL4S","json":"https://pith.science/pith/WAL24DRKKLTJT4CO7BMGDPOL4S.json","graph_json":"https://pith.science/api/pith-number/WAL24DRKKLTJT4CO7BMGDPOL4S/graph.json","events_json":"https://pith.science/api/pith-number/WAL24DRKKLTJT4CO7BMGDPOL4S/events.json","paper":"https://pith.science/paper/WAL24DRK"},"agent_actions":{"view_html":"https://pith.science/pith/WAL24DRKKLTJT4CO7BMGDPOL4S","download_json":"https://pith.science/pith/WAL24DRKKLTJT4CO7BMGDPOL4S.json","view_paper":"https://pith.science/paper/WAL24DRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1305.2436&json=true","fetch_graph":"https://pith.science/api/pith-number/WAL24DRKKLTJT4CO7BMGDPOL4S/graph.json","fetch_events":"https://pith.science/api/pith-number/WAL24DRKKLTJT4CO7BMGDPOL4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAL24DRKKLTJT4CO7BMGDPOL4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAL24DRKKLTJT4CO7BMGDPOL4S/action/storage_attestation","attest_author":"https://pith.science/pith/WAL24DRKKLTJT4CO7BMGDPOL4S/action/author_attestation","sign_citation":"https://pith.science/pith/WAL24DRKKLTJT4CO7BMGDPOL4S/action/citation_signature","submit_replication":"https://pith.science/pith/WAL24DRKKLTJT4CO7BMGDPOL4S/action/replication_record"}},"created_at":"2026-05-18T02:30:15.916952+00:00","updated_at":"2026-05-18T02:30:15.916952+00:00"}