{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FLKXMUATJ4NJMMCWGKKGOXMDRJ","short_pith_number":"pith:FLKXMUAT","schema_version":"1.0","canonical_sha256":"2ad57650134f1a9630563294675d838a5ce1ad76eaa2606ca6c118c826a1dc07","source":{"kind":"arxiv","id":"2210.13831","version":3},"attestation_state":"computed","paper":{"title":"Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Adrien Taylor, Eduard Gorbunov, Gauthier Gidel, Samuel Horv\\'ath","submitted_at":"2022-10-25T08:21:25Z","abstract_excerpt":"Algorithms for min-max optimization and variational inequalities are often studied under monotonicity assumptions. Motivated by non-monotone machine learning applications, we follow the line of works [Diakonikolas et al., 2021, Lee and Kim, 2021, Pethick et al., 2022, B\\\"ohm, 2022] aiming at going beyond monotonicity by considering the weaker negative comonotonicity assumption. In particular, we provide tight complexity analyses for the Proximal Point, Extragradient, and Optimistic Gradient methods in this setup, closing some questions on their working guarantees beyond monotonicity."},"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":"2210.13831","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-10-25T08:21:25Z","cross_cats_sorted":[],"title_canon_sha256":"dc7d3bf8670aac252ecb4d86f28ff0f277d249295dfc57b7f0412e8c61b65840","abstract_canon_sha256":"52275b374c1b2effe572ffa24343a9440097ab82d893e4699949f71c65914978"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:02.027704Z","signature_b64":"ZhwH+W3qzHWkeH/0ZyU3voyVWoNv3ofrDfX5fIWir7r6sMwNJPXzWmggl5m3qpQm0+P86/S3h3GYHMvRbnsYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ad57650134f1a9630563294675d838a5ce1ad76eaa2606ca6c118c826a1dc07","last_reissued_at":"2026-07-05T06:32:02.027229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:02.027229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Adrien Taylor, Eduard Gorbunov, Gauthier Gidel, Samuel Horv\\'ath","submitted_at":"2022-10-25T08:21:25Z","abstract_excerpt":"Algorithms for min-max optimization and variational inequalities are often studied under monotonicity assumptions. Motivated by non-monotone machine learning applications, we follow the line of works [Diakonikolas et al., 2021, Lee and Kim, 2021, Pethick et al., 2022, B\\\"ohm, 2022] aiming at going beyond monotonicity by considering the weaker negative comonotonicity assumption. In particular, we provide tight complexity analyses for the Proximal Point, Extragradient, and Optimistic Gradient methods in this setup, closing some questions on their working guarantees beyond monotonicity."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13831","kind":"arxiv","version":3},"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/2210.13831/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":"2210.13831","created_at":"2026-07-05T06:32:02.027284+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.13831v3","created_at":"2026-07-05T06:32:02.027284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13831","created_at":"2026-07-05T06:32:02.027284+00:00"},{"alias_kind":"pith_short_12","alias_value":"FLKXMUATJ4NJ","created_at":"2026-07-05T06:32:02.027284+00:00"},{"alias_kind":"pith_short_16","alias_value":"FLKXMUATJ4NJMMCW","created_at":"2026-07-05T06:32:02.027284+00:00"},{"alias_kind":"pith_short_8","alias_value":"FLKXMUAT","created_at":"2026-07-05T06:32:02.027284+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.07529","citing_title":"Training Deep Learning Models with Norm-Constrained LMOs","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FLKXMUATJ4NJMMCWGKKGOXMDRJ","json":"https://pith.science/pith/FLKXMUATJ4NJMMCWGKKGOXMDRJ.json","graph_json":"https://pith.science/api/pith-number/FLKXMUATJ4NJMMCWGKKGOXMDRJ/graph.json","events_json":"https://pith.science/api/pith-number/FLKXMUATJ4NJMMCWGKKGOXMDRJ/events.json","paper":"https://pith.science/paper/FLKXMUAT"},"agent_actions":{"view_html":"https://pith.science/pith/FLKXMUATJ4NJMMCWGKKGOXMDRJ","download_json":"https://pith.science/pith/FLKXMUATJ4NJMMCWGKKGOXMDRJ.json","view_paper":"https://pith.science/paper/FLKXMUAT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.13831&json=true","fetch_graph":"https://pith.science/api/pith-number/FLKXMUATJ4NJMMCWGKKGOXMDRJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FLKXMUATJ4NJMMCWGKKGOXMDRJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FLKXMUATJ4NJMMCWGKKGOXMDRJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FLKXMUATJ4NJMMCWGKKGOXMDRJ/action/storage_attestation","attest_author":"https://pith.science/pith/FLKXMUATJ4NJMMCWGKKGOXMDRJ/action/author_attestation","sign_citation":"https://pith.science/pith/FLKXMUATJ4NJMMCWGKKGOXMDRJ/action/citation_signature","submit_replication":"https://pith.science/pith/FLKXMUATJ4NJMMCWGKKGOXMDRJ/action/replication_record"}},"created_at":"2026-07-05T06:32:02.027284+00:00","updated_at":"2026-07-05T06:32:02.027284+00:00"}