{"id":"W6979306437","doi":"","title":"Wasserstein Distributionally Robust Shallow Convex Neural Networks","year":2024,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Hydro-Québec","keywords":"Artificial neural network; Convex optimization; Context (archaeology); Stability (learning theory); Benchmark (surveying); Regular polygon; Nonlinear system; Scalability","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.00007047632,0.0001579911,0.0001205055,0.0000738062,0.00007891854,0.00006400478,0.0001832437,0.0000977468,0.0001529338],"category_scores_gemma":[0.000006202509,0.0001772111,0.0001052754,0.0004584925,0.00004322471,0.0002590282,0.00004419974,0.0002450425,0.00005400965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001047555,"about_ca_system_score_gemma":0.00001429465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001425279,"about_ca_topic_score_gemma":0.00003740611,"domain_scores_codex":[0.9992921,0.00001752471,0.0001009808,0.0002589659,0.00003794363,0.0002925318],"domain_scores_gemma":[0.9996238,0.00007416869,0.00001146392,0.0001569701,0.00002386412,0.0001097348],"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":[0.000005598971,0.000005574371,0.001348388,0.00002941448,0.00005540654,0.000314713,0.00001972291,0.9478257,0.00004974773,0.04927427,0.0006855022,0.0003859622],"study_design_scores_gemma":[0.0001260519,0.00001554569,0.0003597924,0.00004874573,0.00003264827,0.00001059179,0.00003360053,0.9957175,0.00004212707,0.0003365537,0.003072682,0.0002042233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6335497,0.000756829,0.351382,0.00004252673,0.001399463,0.00006896825,0.00003032579,0.001119243,0.01165093],"genre_scores_gemma":[0.9985262,0.00007374092,0.00003810863,0.00002144464,0.0001784996,2.983932e-7,0.00006267188,0.00002700477,0.001072002],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3649766,"threshold_uncertainty_score":0.722646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03467961227404202,"score_gpt":0.148782168062044,"score_spread":0.114102555788002,"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."}}