{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HY3D7A3GGX7URKO2WEROZCLLQE","short_pith_number":"pith:HY3D7A3G","schema_version":"1.0","canonical_sha256":"3e363f836635ff48a9dab122ec896b81106d1d574f80bf5b85bc97ccb8375027","source":{"kind":"arxiv","id":"2006.10138","version":5},"attestation_state":"computed","paper":{"title":"An Online Method for A Class of Distributionally Robust Optimization with Non-Convex Objectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Qi Qi, Rong Jin, Tianbao Yang, Yi Xu, Zhishuai Guo","submitted_at":"2020-06-17T20:19:25Z","abstract_excerpt":"In this paper, we propose a practical online method for solving a class of distributionally robust optimization (DRO) with non-convex objectives, which has important applications in machine learning for improving the robustness of neural networks. In the literature, most methods for solving DRO are based on stochastic primal-dual methods. However, primal-dual methods for DRO suffer from several drawbacks: (1) manipulating a high-dimensional dual variable corresponding to the size of data is time expensive; (2) they are not friendly to online learning where data is coming sequentially. To addre"},"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":"2006.10138","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-17T20:19:25Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"4ba1bc232297f4ea7ca79ed32a83a77615b970f3ded9b218718f78d9cc67e8da","abstract_canon_sha256":"a25e0097487725d74223756a137a12b98946813359573c77ec6eebf033c5defb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:12.072990Z","signature_b64":"A209ZRm/qEC6tec2JzEGbt7rsuyo6FhWS9t2DZGjOI3XYZe4SYr88nobMbnSALP+iUZPsw4Rwf2MWTLwn81zCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e363f836635ff48a9dab122ec896b81106d1d574f80bf5b85bc97ccb8375027","last_reissued_at":"2026-07-05T03:31:12.072595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:12.072595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Online Method for A Class of Distributionally Robust Optimization with Non-Convex Objectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Qi Qi, Rong Jin, Tianbao Yang, Yi Xu, Zhishuai Guo","submitted_at":"2020-06-17T20:19:25Z","abstract_excerpt":"In this paper, we propose a practical online method for solving a class of distributionally robust optimization (DRO) with non-convex objectives, which has important applications in machine learning for improving the robustness of neural networks. In the literature, most methods for solving DRO are based on stochastic primal-dual methods. However, primal-dual methods for DRO suffer from several drawbacks: (1) manipulating a high-dimensional dual variable corresponding to the size of data is time expensive; (2) they are not friendly to online learning where data is coming sequentially. To addre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10138","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/2006.10138/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":"2006.10138","created_at":"2026-07-05T03:31:12.072652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.10138v5","created_at":"2026-07-05T03:31:12.072652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10138","created_at":"2026-07-05T03:31:12.072652+00:00"},{"alias_kind":"pith_short_12","alias_value":"HY3D7A3GGX7U","created_at":"2026-07-05T03:31:12.072652+00:00"},{"alias_kind":"pith_short_16","alias_value":"HY3D7A3GGX7URKO2","created_at":"2026-07-05T03:31:12.072652+00:00"},{"alias_kind":"pith_short_8","alias_value":"HY3D7A3G","created_at":"2026-07-05T03:31:12.072652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20380","citing_title":"GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HY3D7A3GGX7URKO2WEROZCLLQE","json":"https://pith.science/pith/HY3D7A3GGX7URKO2WEROZCLLQE.json","graph_json":"https://pith.science/api/pith-number/HY3D7A3GGX7URKO2WEROZCLLQE/graph.json","events_json":"https://pith.science/api/pith-number/HY3D7A3GGX7URKO2WEROZCLLQE/events.json","paper":"https://pith.science/paper/HY3D7A3G"},"agent_actions":{"view_html":"https://pith.science/pith/HY3D7A3GGX7URKO2WEROZCLLQE","download_json":"https://pith.science/pith/HY3D7A3GGX7URKO2WEROZCLLQE.json","view_paper":"https://pith.science/paper/HY3D7A3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.10138&json=true","fetch_graph":"https://pith.science/api/pith-number/HY3D7A3GGX7URKO2WEROZCLLQE/graph.json","fetch_events":"https://pith.science/api/pith-number/HY3D7A3GGX7URKO2WEROZCLLQE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HY3D7A3GGX7URKO2WEROZCLLQE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HY3D7A3GGX7URKO2WEROZCLLQE/action/storage_attestation","attest_author":"https://pith.science/pith/HY3D7A3GGX7URKO2WEROZCLLQE/action/author_attestation","sign_citation":"https://pith.science/pith/HY3D7A3GGX7URKO2WEROZCLLQE/action/citation_signature","submit_replication":"https://pith.science/pith/HY3D7A3GGX7URKO2WEROZCLLQE/action/replication_record"}},"created_at":"2026-07-05T03:31:12.072652+00:00","updated_at":"2026-07-05T03:31:12.072652+00:00"}