{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6HYZZLOM2ZFHE2OU3XJPVWYYX7","short_pith_number":"pith:6HYZZLOM","schema_version":"1.0","canonical_sha256":"f1f19cadccd64a7269d4ddd2fadb18bfd6e83fcbabb6a182fdf0a92f93bfead5","source":{"kind":"arxiv","id":"2411.15769","version":2},"attestation_state":"computed","paper":{"title":"Gradient Norm Regularization Second-Order Algorithms for Solving Nonconvex-Strongly Concave Minimax Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Jun-Lin Wang, Zi Xu","submitted_at":"2024-11-24T09:46:36Z","abstract_excerpt":"In this paper, we study second-order algorithms for solving nonconvex-strongly concave minimax problems, which have attracted much attention in recent years in many fields, especially in machine learning.We propose a gradient norm regularized trust-region (GRTR) algorithm to solve nonconvex-strongly concave minimax problems, where the objective function of the trust-region subproblem in each iteration uses a regularized version of the Hessian matrix, and the regularization coefficient and the radius of the ball constraint are proportional to the square root of the gradient norm. The iteration "},"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":"2411.15769","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-11-24T09:46:36Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"b8c1798910acf616b4f6c21b368a21a2b351a97b03a9ff5284a066bf4b90e9b4","abstract_canon_sha256":"4b900c030314349c194d29e546c7dbb5695e2667165ce5dea4e81a15d3a6b5dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:38.515616Z","signature_b64":"y+LgSvmr3q4AW3VipgamFY0IFtIjVZMZvNg5u6mPr+IUXuRAOnrjpVKQusb6OTEP5z2NfIb5sYjZIhgO2nVzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1f19cadccd64a7269d4ddd2fadb18bfd6e83fcbabb6a182fdf0a92f93bfead5","last_reissued_at":"2026-07-05T11:21:38.515039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:38.515039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Norm Regularization Second-Order Algorithms for Solving Nonconvex-Strongly Concave Minimax Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Jun-Lin Wang, Zi Xu","submitted_at":"2024-11-24T09:46:36Z","abstract_excerpt":"In this paper, we study second-order algorithms for solving nonconvex-strongly concave minimax problems, which have attracted much attention in recent years in many fields, especially in machine learning.We propose a gradient norm regularized trust-region (GRTR) algorithm to solve nonconvex-strongly concave minimax problems, where the objective function of the trust-region subproblem in each iteration uses a regularized version of the Hessian matrix, and the regularization coefficient and the radius of the ball constraint are proportional to the square root of the gradient norm. The iteration "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15769","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.15769/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":"2411.15769","created_at":"2026-07-05T11:21:38.515101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15769v2","created_at":"2026-07-05T11:21:38.515101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15769","created_at":"2026-07-05T11:21:38.515101+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HYZZLOM2ZFH","created_at":"2026-07-05T11:21:38.515101+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HYZZLOM2ZFHE2OU","created_at":"2026-07-05T11:21:38.515101+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HYZZLOM","created_at":"2026-07-05T11:21:38.515101+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.04807","citing_title":"A Fast Newton Method Under Local Lipschitz Smoothness","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6HYZZLOM2ZFHE2OU3XJPVWYYX7","json":"https://pith.science/pith/6HYZZLOM2ZFHE2OU3XJPVWYYX7.json","graph_json":"https://pith.science/api/pith-number/6HYZZLOM2ZFHE2OU3XJPVWYYX7/graph.json","events_json":"https://pith.science/api/pith-number/6HYZZLOM2ZFHE2OU3XJPVWYYX7/events.json","paper":"https://pith.science/paper/6HYZZLOM"},"agent_actions":{"view_html":"https://pith.science/pith/6HYZZLOM2ZFHE2OU3XJPVWYYX7","download_json":"https://pith.science/pith/6HYZZLOM2ZFHE2OU3XJPVWYYX7.json","view_paper":"https://pith.science/paper/6HYZZLOM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15769&json=true","fetch_graph":"https://pith.science/api/pith-number/6HYZZLOM2ZFHE2OU3XJPVWYYX7/graph.json","fetch_events":"https://pith.science/api/pith-number/6HYZZLOM2ZFHE2OU3XJPVWYYX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HYZZLOM2ZFHE2OU3XJPVWYYX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HYZZLOM2ZFHE2OU3XJPVWYYX7/action/storage_attestation","attest_author":"https://pith.science/pith/6HYZZLOM2ZFHE2OU3XJPVWYYX7/action/author_attestation","sign_citation":"https://pith.science/pith/6HYZZLOM2ZFHE2OU3XJPVWYYX7/action/citation_signature","submit_replication":"https://pith.science/pith/6HYZZLOM2ZFHE2OU3XJPVWYYX7/action/replication_record"}},"created_at":"2026-07-05T11:21:38.515101+00:00","updated_at":"2026-07-05T11:21:38.515101+00:00"}