{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SRTRVJXUWQSVFSFTLZ3RGKHA2T","short_pith_number":"pith:SRTRVJXU","schema_version":"1.0","canonical_sha256":"94671aa6f4b42552c8b35e771328e0d4eba1d4ce06d8509a6b767f01ca659bc1","source":{"kind":"arxiv","id":"1805.11640","version":2},"attestation_state":"computed","paper":{"title":"K-Beam Minimax: Efficient Optimization for Deep Adversarial Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jihun Hamm, Yung-Kyun Noh","submitted_at":"2018-05-29T18:30:12Z","abstract_excerpt":"Minimax optimization plays a key role in adversarial training of machine learning algorithms, such as learning generative models, domain adaptation, privacy preservation, and robust learning. In this paper, we demonstrate the failure of alternating gradient descent in minimax optimization problems due to the discontinuity of solutions of the inner maximization. To address this, we propose a new epsilon-subgradient descent algorithm that addresses this problem by simultaneously tracking K candidate solutions. Practically, the algorithm can find solutions that previous saddle-point algorithms ca"},"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":"1805.11640","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T18:30:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"79ab80ec3a8ea8c0e867d6cb3aec3be98224db4618794e9e2208df5f2495e663","abstract_canon_sha256":"9c9b6e84a282005cf2082bded72abdfec8cce28149a889019560129138c07d03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:57.372862Z","signature_b64":"6c/Aahntcx1PQANNL4tQGWS503LK7PLABLO1lRxj+Xa6c2H2EPLaBT33mTAVPQ6hMWYilSE/81wcLtKKrnnlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94671aa6f4b42552c8b35e771328e0d4eba1d4ce06d8509a6b767f01ca659bc1","last_reissued_at":"2026-05-18T00:13:57.372169Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:57.372169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"K-Beam Minimax: Efficient Optimization for Deep Adversarial Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jihun Hamm, Yung-Kyun Noh","submitted_at":"2018-05-29T18:30:12Z","abstract_excerpt":"Minimax optimization plays a key role in adversarial training of machine learning algorithms, such as learning generative models, domain adaptation, privacy preservation, and robust learning. In this paper, we demonstrate the failure of alternating gradient descent in minimax optimization problems due to the discontinuity of solutions of the inner maximization. To address this, we propose a new epsilon-subgradient descent algorithm that addresses this problem by simultaneously tracking K candidate solutions. Practically, the algorithm can find solutions that previous saddle-point algorithms ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11640","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":"1805.11640","created_at":"2026-05-18T00:13:57.372288+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.11640v2","created_at":"2026-05-18T00:13:57.372288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11640","created_at":"2026-05-18T00:13:57.372288+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRTRVJXUWQSV","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRTRVJXUWQSVFSFT","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRTRVJXU","created_at":"2026-05-18T12:32:53.628368+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/SRTRVJXUWQSVFSFTLZ3RGKHA2T","json":"https://pith.science/pith/SRTRVJXUWQSVFSFTLZ3RGKHA2T.json","graph_json":"https://pith.science/api/pith-number/SRTRVJXUWQSVFSFTLZ3RGKHA2T/graph.json","events_json":"https://pith.science/api/pith-number/SRTRVJXUWQSVFSFTLZ3RGKHA2T/events.json","paper":"https://pith.science/paper/SRTRVJXU"},"agent_actions":{"view_html":"https://pith.science/pith/SRTRVJXUWQSVFSFTLZ3RGKHA2T","download_json":"https://pith.science/pith/SRTRVJXUWQSVFSFTLZ3RGKHA2T.json","view_paper":"https://pith.science/paper/SRTRVJXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.11640&json=true","fetch_graph":"https://pith.science/api/pith-number/SRTRVJXUWQSVFSFTLZ3RGKHA2T/graph.json","fetch_events":"https://pith.science/api/pith-number/SRTRVJXUWQSVFSFTLZ3RGKHA2T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRTRVJXUWQSVFSFTLZ3RGKHA2T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRTRVJXUWQSVFSFTLZ3RGKHA2T/action/storage_attestation","attest_author":"https://pith.science/pith/SRTRVJXUWQSVFSFTLZ3RGKHA2T/action/author_attestation","sign_citation":"https://pith.science/pith/SRTRVJXUWQSVFSFTLZ3RGKHA2T/action/citation_signature","submit_replication":"https://pith.science/pith/SRTRVJXUWQSVFSFTLZ3RGKHA2T/action/replication_record"}},"created_at":"2026-05-18T00:13:57.372288+00:00","updated_at":"2026-05-18T00:13:57.372288+00:00"}