{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JQN7BY4PLWUB5UWPYWWQK567IC","short_pith_number":"pith:JQN7BY4P","schema_version":"1.0","canonical_sha256":"4c1bf0e38f5da81ed2cfc5ad0577df40a3103bddf7396c35916e8ebea339d2d7","source":{"kind":"arxiv","id":"2403.03562","version":2},"attestation_state":"computed","paper":{"title":"Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dingzhi Yu, Lijun Zhang, Wei Jiang, Yunuo Cai","submitted_at":"2024-03-06T09:14:24Z","abstract_excerpt":"In this paper, we investigate the empirical counterpart of Group Distributionally Robust Optimization (GDRO), which aims to minimize the maximal empirical risk across $m$ distinct groups. We formulate empirical GDRO as a $\\textit{two-level}$ finite-sum convex-concave minimax optimization problem and develop an algorithm called ALEG to benefit from its special structure. ALEG is a double-looped stochastic primal-dual algorithm that incorporates variance reduction techniques into a modified mirror prox routine. To exploit the two-level finite-sum structure, we propose a simple group sampling str"},"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":"2403.03562","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-06T09:14:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2f5941aa8248976481545c1cb669628f73f4675c42df3dc10dd18b159fb407ad","abstract_canon_sha256":"f05e9422488963628b27f7218bfd430fcc94bb1e863fdd5e3a98fc696c4ff16f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:19.894297Z","signature_b64":"NO3dojq5FyE33/K/3vdLpJTEgSDC1DwXih5gQBwbXkqxq6RZZHGNeFIw6uIwc4nq0PN7wpkKJ/YZuqW1AOqkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c1bf0e38f5da81ed2cfc5ad0577df40a3103bddf7396c35916e8ebea339d2d7","last_reissued_at":"2026-07-05T09:09:19.893808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:19.893808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dingzhi Yu, Lijun Zhang, Wei Jiang, Yunuo Cai","submitted_at":"2024-03-06T09:14:24Z","abstract_excerpt":"In this paper, we investigate the empirical counterpart of Group Distributionally Robust Optimization (GDRO), which aims to minimize the maximal empirical risk across $m$ distinct groups. We formulate empirical GDRO as a $\\textit{two-level}$ finite-sum convex-concave minimax optimization problem and develop an algorithm called ALEG to benefit from its special structure. ALEG is a double-looped stochastic primal-dual algorithm that incorporates variance reduction techniques into a modified mirror prox routine. To exploit the two-level finite-sum structure, we propose a simple group sampling str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03562","kind":"arxiv","version":2},"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/2403.03562/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":"2403.03562","created_at":"2026-07-05T09:09:19.893868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03562v2","created_at":"2026-07-05T09:09:19.893868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03562","created_at":"2026-07-05T09:09:19.893868+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQN7BY4PLWUB","created_at":"2026-07-05T09:09:19.893868+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQN7BY4PLWUB5UWP","created_at":"2026-07-05T09:09:19.893868+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQN7BY4P","created_at":"2026-07-05T09:09:19.893868+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/JQN7BY4PLWUB5UWPYWWQK567IC","json":"https://pith.science/pith/JQN7BY4PLWUB5UWPYWWQK567IC.json","graph_json":"https://pith.science/api/pith-number/JQN7BY4PLWUB5UWPYWWQK567IC/graph.json","events_json":"https://pith.science/api/pith-number/JQN7BY4PLWUB5UWPYWWQK567IC/events.json","paper":"https://pith.science/paper/JQN7BY4P"},"agent_actions":{"view_html":"https://pith.science/pith/JQN7BY4PLWUB5UWPYWWQK567IC","download_json":"https://pith.science/pith/JQN7BY4PLWUB5UWPYWWQK567IC.json","view_paper":"https://pith.science/paper/JQN7BY4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03562&json=true","fetch_graph":"https://pith.science/api/pith-number/JQN7BY4PLWUB5UWPYWWQK567IC/graph.json","fetch_events":"https://pith.science/api/pith-number/JQN7BY4PLWUB5UWPYWWQK567IC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQN7BY4PLWUB5UWPYWWQK567IC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQN7BY4PLWUB5UWPYWWQK567IC/action/storage_attestation","attest_author":"https://pith.science/pith/JQN7BY4PLWUB5UWPYWWQK567IC/action/author_attestation","sign_citation":"https://pith.science/pith/JQN7BY4PLWUB5UWPYWWQK567IC/action/citation_signature","submit_replication":"https://pith.science/pith/JQN7BY4PLWUB5UWPYWWQK567IC/action/replication_record"}},"created_at":"2026-07-05T09:09:19.893868+00:00","updated_at":"2026-07-05T09:09:19.893868+00:00"}