{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QWT4LEBYKYB2NHEDSYAG46URIH","short_pith_number":"pith:QWT4LEBY","schema_version":"1.0","canonical_sha256":"85a7c590385603a69c8396006e7a9141f2c664ac398ba53090a7f400dc419e99","source":{"kind":"arxiv","id":"1810.08750","version":6},"attestation_state":"computed","paper":{"title":"Learning Models with Uniform Performance via Distributionally Robust Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hongseok Namkoong, John Duchi","submitted_at":"2018-10-20T03:50:29Z","abstract_excerpt":"A common goal in statistics and machine learning is to learn models that can perform well against distributional shifts, such as latent heterogeneous subpopulations, unknown covariate shifts, or unmodeled temporal effects. We develop and analyze a distributionally robust stochastic optimization (DRO) framework that learns a model providing good performance against perturbations to the data-generating distribution. We give a convex formulation for the problem, providing several convergence guarantees. We prove finite-sample minimax upper and lower bounds, showing that distributional robustness "},"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":"1810.08750","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-20T03:50:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a4fbdfa831d2a6b2debe10dee3b00e7e893c66ccd2f3ab121fc28c00c5ca86c3","abstract_canon_sha256":"916e17dec686649ad8ba61fb56c371ff591830911f0a7fe85aea3c174d249853"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:20:09.557795Z","signature_b64":"+rtCPEuQmlEUL+goZ+07tm3ol7JTp++rjVF3an+FlLpIw/Ms7oV7WrRxRvrCXJZ+a+nOD0gEqwoVzr+WPHojAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85a7c590385603a69c8396006e7a9141f2c664ac398ba53090a7f400dc419e99","last_reissued_at":"2026-07-05T01:20:09.557311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:20:09.557311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Models with Uniform Performance via Distributionally Robust Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hongseok Namkoong, John Duchi","submitted_at":"2018-10-20T03:50:29Z","abstract_excerpt":"A common goal in statistics and machine learning is to learn models that can perform well against distributional shifts, such as latent heterogeneous subpopulations, unknown covariate shifts, or unmodeled temporal effects. We develop and analyze a distributionally robust stochastic optimization (DRO) framework that learns a model providing good performance against perturbations to the data-generating distribution. We give a convex formulation for the problem, providing several convergence guarantees. We prove finite-sample minimax upper and lower bounds, showing that distributional robustness "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08750","kind":"arxiv","version":6},"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/1810.08750/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":"1810.08750","created_at":"2026-07-05T01:20:09.557375+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.08750v6","created_at":"2026-07-05T01:20:09.557375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08750","created_at":"2026-07-05T01:20:09.557375+00:00"},{"alias_kind":"pith_short_12","alias_value":"QWT4LEBYKYB2","created_at":"2026-07-05T01:20:09.557375+00:00"},{"alias_kind":"pith_short_16","alias_value":"QWT4LEBYKYB2NHED","created_at":"2026-07-05T01:20:09.557375+00:00"},{"alias_kind":"pith_short_8","alias_value":"QWT4LEBY","created_at":"2026-07-05T01:20:09.557375+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09881","citing_title":"Toward Calibrated, Fair, and accurate Deepfake Detection","ref_index":160,"is_internal_anchor":false},{"citing_arxiv_id":"2503.15105","citing_title":"Control, Optimal Transport and Neural Differential Equations in Supervised Learning","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"1911.08731","citing_title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03125","citing_title":"Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QWT4LEBYKYB2NHEDSYAG46URIH","json":"https://pith.science/pith/QWT4LEBYKYB2NHEDSYAG46URIH.json","graph_json":"https://pith.science/api/pith-number/QWT4LEBYKYB2NHEDSYAG46URIH/graph.json","events_json":"https://pith.science/api/pith-number/QWT4LEBYKYB2NHEDSYAG46URIH/events.json","paper":"https://pith.science/paper/QWT4LEBY"},"agent_actions":{"view_html":"https://pith.science/pith/QWT4LEBYKYB2NHEDSYAG46URIH","download_json":"https://pith.science/pith/QWT4LEBYKYB2NHEDSYAG46URIH.json","view_paper":"https://pith.science/paper/QWT4LEBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.08750&json=true","fetch_graph":"https://pith.science/api/pith-number/QWT4LEBYKYB2NHEDSYAG46URIH/graph.json","fetch_events":"https://pith.science/api/pith-number/QWT4LEBYKYB2NHEDSYAG46URIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QWT4LEBYKYB2NHEDSYAG46URIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QWT4LEBYKYB2NHEDSYAG46URIH/action/storage_attestation","attest_author":"https://pith.science/pith/QWT4LEBYKYB2NHEDSYAG46URIH/action/author_attestation","sign_citation":"https://pith.science/pith/QWT4LEBYKYB2NHEDSYAG46URIH/action/citation_signature","submit_replication":"https://pith.science/pith/QWT4LEBYKYB2NHEDSYAG46URIH/action/replication_record"}},"created_at":"2026-07-05T01:20:09.557375+00:00","updated_at":"2026-07-05T01:20:09.557375+00:00"}