{"id":"W4378718490","doi":"10.48550/arxiv.2305.17076","title":"Exact Generalization Guarantees for (Regularized) Wasserstein Distributionally Robust Models","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Probabilistic and Robust Engineering Design","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Discovery Air (Canada)","funders":"Agence Nationale de la Recherche","keywords":"Curse of dimensionality; Generalization; Spurious relationship; Estimator; Mathematical optimization; Computer science; Cover (algebra); Mathematics; Applied mathematics; Artificial intelligence; Statistics; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01488124,0.001993652,0.002392467,0.001248618,0.0007582122,0.002169948,0.003359783,0.003322407,0.002502188],"category_scores_gemma":[0.06243222,0.001099769,0.001860055,0.00129846,0.003425041,0.007994701,0.005444256,0.006577992,0.0006428341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002658705,"about_ca_system_score_gemma":0.001467809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002104048,"about_ca_topic_score_gemma":0.001835074,"domain_scores_codex":[0.9917109,0.003767767,0.0004322919,0.002049434,0.001618308,0.0004211915],"domain_scores_gemma":[0.9620667,0.02612975,0.004108404,0.004968175,0.002060506,0.000666451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001050278,0.00006685493,0.001329131,0.0001832064,0.0001237077,0.0001197197,0.0001850046,0.7154945,0.001453866,0.2466929,0.002186683,0.03205949],"study_design_scores_gemma":[0.000007836818,0.00002977902,0.0002001951,0.00002060163,0.000009804462,0.00003387361,0.00001159683,0.8245049,0.0003575527,0.1743856,0.0004241231,0.00001409187],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01323768,0.0004545737,0.9839242,0.0006587167,0.00002661343,0.00002968436,0.0001589781,0.0002047139,0.001304926],"genre_scores_gemma":[0.7262875,0.001883845,0.2636603,0.001093251,0.0004161962,0.00045385,0.001195645,0.0005921035,0.004417442],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01488124,"threshold_uncertainty_score":0.07870042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3294823376186217,"score_gpt":0.2577434931103554,"score_spread":0.07173884450826629,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}