{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:H7OXMTCL6SJKMN7DUPHYXGGCPA","short_pith_number":"pith:H7OXMTCL","schema_version":"1.0","canonical_sha256":"3fdd764c4bf492a637e3a3cf8b98c2781fb70df0d86f5d84de1ab620b5db315e","source":{"kind":"arxiv","id":"1706.03269","version":1},"attestation_state":"computed","paper":{"title":"An Online Learning Approach to Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Aurelien Lucchi, Kfir Y. Levy, Paulina Grnarova, Thomas Hofmann","submitted_at":"2017-06-10T18:49:07Z","abstract_excerpt":"We consider the problem of training generative models with a Generative Adversarial Network (GAN). Although GANs can accurately model complex distributions, they are known to be difficult to train due to instabilities caused by a difficult minimax optimization problem. In this paper, we view the problem of training GANs as finding a mixed strategy in a zero-sum game. Building on ideas from online learning we propose a novel training method named Chekhov GAN 1 . On the theory side, we show that our method provably converges to an equilibrium for semi-shallow GAN architectures, i.e. architecture"},"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":"1706.03269","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-10T18:49:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1fde7839b0a7f709fdd8117e4c619b10819585d74408f3bf387d58e9dd453322","abstract_canon_sha256":"fc85c880c2f26a1853800dfd3f4b9baec7951a4518fc786fc7844a6f01438c71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:37.969405Z","signature_b64":"D0PZhw7Oz21eduLsQdEaVSMEuEjJ4cWA4lYSdlUIQmmfzU3kRfLBo7pvFx3NdphPf9hoIydQykhMu6JIhExVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fdd764c4bf492a637e3a3cf8b98c2781fb70df0d86f5d84de1ab620b5db315e","last_reissued_at":"2026-05-18T00:42:37.968796Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:37.968796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Online Learning Approach to Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Aurelien Lucchi, Kfir Y. Levy, Paulina Grnarova, Thomas Hofmann","submitted_at":"2017-06-10T18:49:07Z","abstract_excerpt":"We consider the problem of training generative models with a Generative Adversarial Network (GAN). Although GANs can accurately model complex distributions, they are known to be difficult to train due to instabilities caused by a difficult minimax optimization problem. In this paper, we view the problem of training GANs as finding a mixed strategy in a zero-sum game. Building on ideas from online learning we propose a novel training method named Chekhov GAN 1 . On the theory side, we show that our method provably converges to an equilibrium for semi-shallow GAN architectures, i.e. architecture"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.03269","kind":"arxiv","version":1},"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":"1706.03269","created_at":"2026-05-18T00:42:37.968877+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.03269v1","created_at":"2026-05-18T00:42:37.968877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03269","created_at":"2026-05-18T00:42:37.968877+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7OXMTCL6SJK","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7OXMTCL6SJKMN7D","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7OXMTCL","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00229","citing_title":"A unified perspective on fine-tuning and sampling with diffusion and flow models","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7OXMTCL6SJKMN7DUPHYXGGCPA","json":"https://pith.science/pith/H7OXMTCL6SJKMN7DUPHYXGGCPA.json","graph_json":"https://pith.science/api/pith-number/H7OXMTCL6SJKMN7DUPHYXGGCPA/graph.json","events_json":"https://pith.science/api/pith-number/H7OXMTCL6SJKMN7DUPHYXGGCPA/events.json","paper":"https://pith.science/paper/H7OXMTCL"},"agent_actions":{"view_html":"https://pith.science/pith/H7OXMTCL6SJKMN7DUPHYXGGCPA","download_json":"https://pith.science/pith/H7OXMTCL6SJKMN7DUPHYXGGCPA.json","view_paper":"https://pith.science/paper/H7OXMTCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.03269&json=true","fetch_graph":"https://pith.science/api/pith-number/H7OXMTCL6SJKMN7DUPHYXGGCPA/graph.json","fetch_events":"https://pith.science/api/pith-number/H7OXMTCL6SJKMN7DUPHYXGGCPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7OXMTCL6SJKMN7DUPHYXGGCPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7OXMTCL6SJKMN7DUPHYXGGCPA/action/storage_attestation","attest_author":"https://pith.science/pith/H7OXMTCL6SJKMN7DUPHYXGGCPA/action/author_attestation","sign_citation":"https://pith.science/pith/H7OXMTCL6SJKMN7DUPHYXGGCPA/action/citation_signature","submit_replication":"https://pith.science/pith/H7OXMTCL6SJKMN7DUPHYXGGCPA/action/replication_record"}},"created_at":"2026-05-18T00:42:37.968877+00:00","updated_at":"2026-05-18T00:42:37.968877+00:00"}