{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KJSKKJTOEYLRFUEACILZBFG6TG","short_pith_number":"pith:KJSKKJTO","schema_version":"1.0","canonical_sha256":"5264a5266e261712d08012179094de9996b58e0052d71c7800e014afc20e1d36","source":{"kind":"arxiv","id":"1802.10551","version":5},"attestation_state":"computed","paper":{"title":"A Variational Inequality Perspective on Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ga\\\"etan Vignoud, Gauthier Gidel, Hugo Berard, Pascal Vincent, Simon Lacoste-Julien","submitted_at":"2018-02-28T17:40:05Z","abstract_excerpt":"Generative adversarial networks (GANs) form a generative modeling approach known for producing appealing samples, but they are notably difficult to train. One common way to tackle this issue has been to propose new formulations of the GAN objective. Yet, surprisingly few studies have looked at optimization methods designed for this adversarial training. In this work, we cast GAN optimization problems in the general variational inequality framework. Tapping into the mathematical programming literature, we counter some common misconceptions about the difficulties of saddle point optimization and"},"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":"1802.10551","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-28T17:40:05Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"f756e533c44d338f0b49f3f2be6ce567bbd2acc97accd128d504b76af1067738","abstract_canon_sha256":"56c72f60a2cfa3ce17954f08cacdb44dca9ef06d1e3bfd3e958792d2efa5f962"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:31:19.676382Z","signature_b64":"EaGcJpnH9f/x5ig8x8tig2TLpGP55ULbM400q0IHz28PEJZlv5ScXj2BqN/1+FxpAINDbzzdz9kcR/8ySDeFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5264a5266e261712d08012179094de9996b58e0052d71c7800e014afc20e1d36","last_reissued_at":"2026-07-05T01:31:19.675799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:31:19.675799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Variational Inequality Perspective on Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ga\\\"etan Vignoud, Gauthier Gidel, Hugo Berard, Pascal Vincent, Simon Lacoste-Julien","submitted_at":"2018-02-28T17:40:05Z","abstract_excerpt":"Generative adversarial networks (GANs) form a generative modeling approach known for producing appealing samples, but they are notably difficult to train. One common way to tackle this issue has been to propose new formulations of the GAN objective. Yet, surprisingly few studies have looked at optimization methods designed for this adversarial training. In this work, we cast GAN optimization problems in the general variational inequality framework. Tapping into the mathematical programming literature, we counter some common misconceptions about the difficulties of saddle point optimization and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10551","kind":"arxiv","version":5},"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/1802.10551/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":"1802.10551","created_at":"2026-07-05T01:31:19.675881+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.10551v5","created_at":"2026-07-05T01:31:19.675881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10551","created_at":"2026-07-05T01:31:19.675881+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJSKKJTOEYLR","created_at":"2026-07-05T01:31:19.675881+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJSKKJTOEYLRFUEA","created_at":"2026-07-05T01:31:19.675881+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJSKKJTO","created_at":"2026-07-05T01:31:19.675881+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00778","citing_title":"A path-following framework on fiber bundle for variational inequalities","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2409.13428","citing_title":"Methods for Solving Variational Inequalities with Markovian Stochasticity","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22644","citing_title":"Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2502.07529","citing_title":"Training Deep Learning Models with Norm-Constrained LMOs","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16262","citing_title":"Mirror Descent-Type Algorithms for the Variational Inequality Problem with Functional Constraints","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18809","citing_title":"Metric-Gradient Projection for Stable Multi-Agent Policy Learning","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJSKKJTOEYLRFUEACILZBFG6TG","json":"https://pith.science/pith/KJSKKJTOEYLRFUEACILZBFG6TG.json","graph_json":"https://pith.science/api/pith-number/KJSKKJTOEYLRFUEACILZBFG6TG/graph.json","events_json":"https://pith.science/api/pith-number/KJSKKJTOEYLRFUEACILZBFG6TG/events.json","paper":"https://pith.science/paper/KJSKKJTO"},"agent_actions":{"view_html":"https://pith.science/pith/KJSKKJTOEYLRFUEACILZBFG6TG","download_json":"https://pith.science/pith/KJSKKJTOEYLRFUEACILZBFG6TG.json","view_paper":"https://pith.science/paper/KJSKKJTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.10551&json=true","fetch_graph":"https://pith.science/api/pith-number/KJSKKJTOEYLRFUEACILZBFG6TG/graph.json","fetch_events":"https://pith.science/api/pith-number/KJSKKJTOEYLRFUEACILZBFG6TG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJSKKJTOEYLRFUEACILZBFG6TG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJSKKJTOEYLRFUEACILZBFG6TG/action/storage_attestation","attest_author":"https://pith.science/pith/KJSKKJTOEYLRFUEACILZBFG6TG/action/author_attestation","sign_citation":"https://pith.science/pith/KJSKKJTOEYLRFUEACILZBFG6TG/action/citation_signature","submit_replication":"https://pith.science/pith/KJSKKJTOEYLRFUEACILZBFG6TG/action/replication_record"}},"created_at":"2026-07-05T01:31:19.675881+00:00","updated_at":"2026-07-05T01:31:19.675881+00:00"}