{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:I53UEPPGLSDACEFSNP36USASWU","short_pith_number":"pith:I53UEPPG","schema_version":"1.0","canonical_sha256":"4777423de65c860110b26bf7ea4812b51597d9925a62a1b4a713704599d04403","source":{"kind":"arxiv","id":"2001.07819","version":2},"attestation_state":"computed","paper":{"title":"Zeroth-Order Algorithms for Nonconvex Minimax Problems with Improved Complexities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Krishnakumar Balasubramanian, Meisam Razaviyayn, Shiqian Ma, Zhongruo Wang","submitted_at":"2020-01-22T00:05:14Z","abstract_excerpt":"In this paper, we study zeroth-order algorithms for minimax optimization problems that are nonconvex in one variable and strongly-concave in the other variable. Such minimax optimization problems have attracted significant attention lately due to their applications in modern machine learning tasks. We first consider a deterministic version of the problem. We design and analyze the Zeroth-Order Gradient Descent Ascent (\\texttt{ZO-GDA}) algorithm, and provide improved results compared to existing works, in terms of oracle complexity. We also propose the Zeroth-Order Gradient Descent Multi-Step A"},"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":"2001.07819","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2020-01-22T00:05:14Z","cross_cats_sorted":["cs.DS","cs.LG","math.OC"],"title_canon_sha256":"7d0852e4e952cd64e11fb70bbca496a5594ab6a26b5680366947a268aee6c212","abstract_canon_sha256":"d86540f8f2627f4204b388d99652ba9b0cea2ffdbf76f1ffc3a630965e521eb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:22.534480Z","signature_b64":"R9R+XxliCXNck90zzQtAdOlMbUVh1kSmhX922NH955FzkV8zaEyC1fCXkO1S7yqeJ/c4tYny4OcEni4NcbQrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4777423de65c860110b26bf7ea4812b51597d9925a62a1b4a713704599d04403","last_reissued_at":"2026-07-05T04:11:22.533923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:22.533923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zeroth-Order Algorithms for Nonconvex Minimax Problems with Improved Complexities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Krishnakumar Balasubramanian, Meisam Razaviyayn, Shiqian Ma, Zhongruo Wang","submitted_at":"2020-01-22T00:05:14Z","abstract_excerpt":"In this paper, we study zeroth-order algorithms for minimax optimization problems that are nonconvex in one variable and strongly-concave in the other variable. Such minimax optimization problems have attracted significant attention lately due to their applications in modern machine learning tasks. We first consider a deterministic version of the problem. We design and analyze the Zeroth-Order Gradient Descent Ascent (\\texttt{ZO-GDA}) algorithm, and provide improved results compared to existing works, in terms of oracle complexity. We also propose the Zeroth-Order Gradient Descent Multi-Step A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.07819","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/2001.07819/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":"2001.07819","created_at":"2026-07-05T04:11:22.533998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.07819v2","created_at":"2026-07-05T04:11:22.533998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.07819","created_at":"2026-07-05T04:11:22.533998+00:00"},{"alias_kind":"pith_short_12","alias_value":"I53UEPPGLSDA","created_at":"2026-07-05T04:11:22.533998+00:00"},{"alias_kind":"pith_short_16","alias_value":"I53UEPPGLSDACEFS","created_at":"2026-07-05T04:11:22.533998+00:00"},{"alias_kind":"pith_short_8","alias_value":"I53UEPPG","created_at":"2026-07-05T04:11:22.533998+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.01126","citing_title":"Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25372","citing_title":"From Cursed to Competitive: Closing the ZO-FO Gap via Input-to-State Stability","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00650","citing_title":"AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I53UEPPGLSDACEFSNP36USASWU","json":"https://pith.science/pith/I53UEPPGLSDACEFSNP36USASWU.json","graph_json":"https://pith.science/api/pith-number/I53UEPPGLSDACEFSNP36USASWU/graph.json","events_json":"https://pith.science/api/pith-number/I53UEPPGLSDACEFSNP36USASWU/events.json","paper":"https://pith.science/paper/I53UEPPG"},"agent_actions":{"view_html":"https://pith.science/pith/I53UEPPGLSDACEFSNP36USASWU","download_json":"https://pith.science/pith/I53UEPPGLSDACEFSNP36USASWU.json","view_paper":"https://pith.science/paper/I53UEPPG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.07819&json=true","fetch_graph":"https://pith.science/api/pith-number/I53UEPPGLSDACEFSNP36USASWU/graph.json","fetch_events":"https://pith.science/api/pith-number/I53UEPPGLSDACEFSNP36USASWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I53UEPPGLSDACEFSNP36USASWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I53UEPPGLSDACEFSNP36USASWU/action/storage_attestation","attest_author":"https://pith.science/pith/I53UEPPGLSDACEFSNP36USASWU/action/author_attestation","sign_citation":"https://pith.science/pith/I53UEPPGLSDACEFSNP36USASWU/action/citation_signature","submit_replication":"https://pith.science/pith/I53UEPPGLSDACEFSNP36USASWU/action/replication_record"}},"created_at":"2026-07-05T04:11:22.533998+00:00","updated_at":"2026-07-05T04:11:22.533998+00:00"}