{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00179654,0.0004064373,0.0005883885,0.0004585782,0.0002823265,0.0002461634,0.001651986,0.0004944883,0.00006640625],"category_scores_gemma":[0.001231195,0.0003884102,0.0004875346,0.0009648254,0.0001467844,0.0003577107,0.0007332153,0.0003274165,0.00010858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003209665,"about_ca_system_score_gemma":0.0003421637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006571991,"about_ca_topic_score_gemma":0.00003588359,"domain_scores_codex":[0.9968681,0.00018695,0.0005786036,0.001489554,0.0004140113,0.00046283],"domain_scores_gemma":[0.9963782,0.001023511,0.0003950205,0.001207729,0.0008175144,0.0001780346],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006189076,0.00003600099,0.0001176841,0.00004011084,0.00006917518,0.00002602566,0.00003444976,0.7527305,0.00003537978,0.2420786,0.004716414,0.00005375413],"study_design_scores_gemma":[0.000334974,0.00002198507,0.000188162,0.00005241065,0.00007556807,0.000001065666,0.00005778252,0.6201384,0.00002070651,0.3785265,0.0002948698,0.0002875776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02259303,0.0000671918,0.9742093,0.0002102407,0.001046469,0.0007126646,0.0005857644,0.0003343352,0.0002410167],"genre_scores_gemma":[0.9779815,0.000109409,0.007286968,0.00003131841,0.0002082552,0.00001064819,0.0005553659,0.00005515944,0.01376136],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9669223,"threshold_uncertainty_score":0.9998568,"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."}}