{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RBCFW44OZ4US3IYY5ZJURNBHJI","short_pith_number":"pith:RBCFW44O","schema_version":"1.0","canonical_sha256":"88445b738ecf292da318ee5348b4274a3037215151db83000065cc2bf93735c4","source":{"kind":"arxiv","id":"2007.04202","version":1},"attestation_state":"computed","paper":{"title":"Stochastic Hamiltonian Gradient Methods for Smooth Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexia Jolicoeur-Martineau, Hugo Berard, Ioannis Mitliagkas, Nicolas Loizou, Pascal Vincent, Simon Lacoste-Julien","submitted_at":"2020-07-08T15:42:13Z","abstract_excerpt":"The success of adversarial formulations in machine learning has brought renewed motivation for smooth games. In this work, we focus on the class of stochastic Hamiltonian methods and provide the first convergence guarantees for certain classes of stochastic smooth games. We propose a novel unbiased estimator for the stochastic Hamiltonian gradient descent (SHGD) and highlight its benefits. Using tools from the optimization literature we show that SHGD converges linearly to the neighbourhood of a stationary point. To guarantee convergence to the exact solution, we analyze SHGD with a decreasing"},"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":"2007.04202","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T15:42:13Z","cross_cats_sorted":["cs.GT","math.OC","stat.ML"],"title_canon_sha256":"508030a5e423e258cb81cfdb84e632dbbb879592e269d47cb795f304415d9b7d","abstract_canon_sha256":"abd553e33923958cec21af3321b647a43ac7b5f76004e09c04b6002de8002ae4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:21.919150Z","signature_b64":"lgKPNQ6brG+uN5KAw4YSYUFmZE3TIjiZJ0NvsakwZkwJ2nWc64rhDKWGK+68mAPNeLHnT1pv2IP0wnzxsD0XDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88445b738ecf292da318ee5348b4274a3037215151db83000065cc2bf93735c4","last_reissued_at":"2026-07-05T01:17:21.918657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:21.918657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Hamiltonian Gradient Methods for Smooth Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexia Jolicoeur-Martineau, Hugo Berard, Ioannis Mitliagkas, Nicolas Loizou, Pascal Vincent, Simon Lacoste-Julien","submitted_at":"2020-07-08T15:42:13Z","abstract_excerpt":"The success of adversarial formulations in machine learning has brought renewed motivation for smooth games. In this work, we focus on the class of stochastic Hamiltonian methods and provide the first convergence guarantees for certain classes of stochastic smooth games. We propose a novel unbiased estimator for the stochastic Hamiltonian gradient descent (SHGD) and highlight its benefits. Using tools from the optimization literature we show that SHGD converges linearly to the neighbourhood of a stationary point. To guarantee convergence to the exact solution, we analyze SHGD with a decreasing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.04202","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.04202/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":"2007.04202","created_at":"2026-07-05T01:17:21.918719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.04202v1","created_at":"2026-07-05T01:17:21.918719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.04202","created_at":"2026-07-05T01:17:21.918719+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBCFW44OZ4US","created_at":"2026-07-05T01:17:21.918719+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBCFW44OZ4US3IYY","created_at":"2026-07-05T01:17:21.918719+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBCFW44O","created_at":"2026-07-05T01:17:21.918719+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/RBCFW44OZ4US3IYY5ZJURNBHJI","json":"https://pith.science/pith/RBCFW44OZ4US3IYY5ZJURNBHJI.json","graph_json":"https://pith.science/api/pith-number/RBCFW44OZ4US3IYY5ZJURNBHJI/graph.json","events_json":"https://pith.science/api/pith-number/RBCFW44OZ4US3IYY5ZJURNBHJI/events.json","paper":"https://pith.science/paper/RBCFW44O"},"agent_actions":{"view_html":"https://pith.science/pith/RBCFW44OZ4US3IYY5ZJURNBHJI","download_json":"https://pith.science/pith/RBCFW44OZ4US3IYY5ZJURNBHJI.json","view_paper":"https://pith.science/paper/RBCFW44O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.04202&json=true","fetch_graph":"https://pith.science/api/pith-number/RBCFW44OZ4US3IYY5ZJURNBHJI/graph.json","fetch_events":"https://pith.science/api/pith-number/RBCFW44OZ4US3IYY5ZJURNBHJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBCFW44OZ4US3IYY5ZJURNBHJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBCFW44OZ4US3IYY5ZJURNBHJI/action/storage_attestation","attest_author":"https://pith.science/pith/RBCFW44OZ4US3IYY5ZJURNBHJI/action/author_attestation","sign_citation":"https://pith.science/pith/RBCFW44OZ4US3IYY5ZJURNBHJI/action/citation_signature","submit_replication":"https://pith.science/pith/RBCFW44OZ4US3IYY5ZJURNBHJI/action/replication_record"}},"created_at":"2026-07-05T01:17:21.918719+00:00","updated_at":"2026-07-05T01:17:21.918719+00:00"}