{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VSF5E2PMYTQPFWRRRG7YDTF5US","short_pith_number":"pith:VSF5E2PM","schema_version":"1.0","canonical_sha256":"ac8bd269ecc4e0f2da3189bf81ccbda496af2af510625fa4aa1a38e414ff0da2","source":{"kind":"arxiv","id":"2111.13162","version":1},"attestation_state":"computed","paper":{"title":"Randomized Stochastic Gradient Descent Ascent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gabriel Peyr\\'e, Marco Cuturi, Othmane Sebbouh","submitted_at":"2021-11-25T16:44:19Z","abstract_excerpt":"An increasing number of machine learning problems, such as robust or adversarial variants of existing algorithms, require minimizing a loss function that is itself defined as a maximum. Carrying a loop of stochastic gradient ascent (SGA) steps on the (inner) maximization problem, followed by an SGD step on the (outer) minimization, is known as Epoch Stochastic Gradient \\textit{Descent Ascent} (ESGDA). While successful in practice, the theoretical analysis of ESGDA remains challenging, with no clear guidance on choices for the inner loop size nor on the interplay between inner/outer step sizes."},"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":"2111.13162","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-25T16:44:19Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"f4da98507defba10dc1d019cc38debfdddda9e1926ea765925811e1ff2815529","abstract_canon_sha256":"cc527307db157f98c2465a9240a9c48f34ea2ab587d179befda4959543e053aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:18.082952Z","signature_b64":"Slxd9eI33synAT11n7K4avaM5Xv7IgTCFCYg9AzdPv6RbZtrSP6uY7kXXJhsSbvN2++ta6Dl/KMz5QRzKzvKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac8bd269ecc4e0f2da3189bf81ccbda496af2af510625fa4aa1a38e414ff0da2","last_reissued_at":"2026-07-05T03:35:18.082574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:18.082574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Randomized Stochastic Gradient Descent Ascent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gabriel Peyr\\'e, Marco Cuturi, Othmane Sebbouh","submitted_at":"2021-11-25T16:44:19Z","abstract_excerpt":"An increasing number of machine learning problems, such as robust or adversarial variants of existing algorithms, require minimizing a loss function that is itself defined as a maximum. Carrying a loop of stochastic gradient ascent (SGA) steps on the (inner) maximization problem, followed by an SGD step on the (outer) minimization, is known as Epoch Stochastic Gradient \\textit{Descent Ascent} (ESGDA). While successful in practice, the theoretical analysis of ESGDA remains challenging, with no clear guidance on choices for the inner loop size nor on the interplay between inner/outer step sizes."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13162","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/2111.13162/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":"2111.13162","created_at":"2026-07-05T03:35:18.082630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13162v1","created_at":"2026-07-05T03:35:18.082630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13162","created_at":"2026-07-05T03:35:18.082630+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSF5E2PMYTQP","created_at":"2026-07-05T03:35:18.082630+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSF5E2PMYTQPFWRR","created_at":"2026-07-05T03:35:18.082630+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSF5E2PM","created_at":"2026-07-05T03:35:18.082630+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/VSF5E2PMYTQPFWRRRG7YDTF5US","json":"https://pith.science/pith/VSF5E2PMYTQPFWRRRG7YDTF5US.json","graph_json":"https://pith.science/api/pith-number/VSF5E2PMYTQPFWRRRG7YDTF5US/graph.json","events_json":"https://pith.science/api/pith-number/VSF5E2PMYTQPFWRRRG7YDTF5US/events.json","paper":"https://pith.science/paper/VSF5E2PM"},"agent_actions":{"view_html":"https://pith.science/pith/VSF5E2PMYTQPFWRRRG7YDTF5US","download_json":"https://pith.science/pith/VSF5E2PMYTQPFWRRRG7YDTF5US.json","view_paper":"https://pith.science/paper/VSF5E2PM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13162&json=true","fetch_graph":"https://pith.science/api/pith-number/VSF5E2PMYTQPFWRRRG7YDTF5US/graph.json","fetch_events":"https://pith.science/api/pith-number/VSF5E2PMYTQPFWRRRG7YDTF5US/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSF5E2PMYTQPFWRRRG7YDTF5US/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSF5E2PMYTQPFWRRRG7YDTF5US/action/storage_attestation","attest_author":"https://pith.science/pith/VSF5E2PMYTQPFWRRRG7YDTF5US/action/author_attestation","sign_citation":"https://pith.science/pith/VSF5E2PMYTQPFWRRRG7YDTF5US/action/citation_signature","submit_replication":"https://pith.science/pith/VSF5E2PMYTQPFWRRRG7YDTF5US/action/replication_record"}},"created_at":"2026-07-05T03:35:18.082630+00:00","updated_at":"2026-07-05T03:35:18.082630+00:00"}