{"id":"W3158885076","doi":"","title":"A Limited-Capacity Minimax Theorem for Non-Convex Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets.","year":2021,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Nash equilibrium; Minimax; Artificial neural network; Minimax theorem; Stochastic game; Computer science; Mathematical economics; Reinforcement learning; Game theory; Regular polygon; Mathematical optimization; Class (philosophy); Artificial intelligence; Mathematics","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003939552,0.0002636571,0.0002997858,0.0001591264,0.0001887988,0.001038106,0.0005771411,0.00009834205,0.0001132059],"category_scores_gemma":[0.002609388,0.0002462641,0.00004791854,0.0002230478,0.0001990897,0.0003561105,0.0003419126,0.0003282006,0.00003216539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005060837,"about_ca_system_score_gemma":0.000149314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002473363,"about_ca_topic_score_gemma":0.0001625418,"domain_scores_codex":[0.998017,0.0001339664,0.0003817105,0.0007061915,0.0004055137,0.0003556295],"domain_scores_gemma":[0.9973974,0.001347949,0.0001783549,0.000287455,0.0006012403,0.0001876109],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000209797,0.00004861552,0.0001149964,0.00001780274,0.00003177011,0.00004669388,0.002264653,0.00143293,0.0007913921,0.6457554,0.000248325,0.3490377],"study_design_scores_gemma":[0.0001119096,0.0002918111,0.0005579062,0.0001025365,0.00001403173,0.00003542638,0.001772199,0.8823326,0.003308175,0.1100332,0.00110714,0.0003330489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01797203,0.00001959612,0.9708611,0.00882578,0.001062574,0.0002490231,0.0001169704,0.0000441985,0.0008487703],"genre_scores_gemma":[0.8283788,0.00007325955,0.1697009,0.000934434,0.0001520945,0.00001784725,0.00002454329,0.00001632535,0.0007018228],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8808997,"threshold_uncertainty_score":0.999999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1327225173430412,"score_gpt":0.3522322219739912,"score_spread":0.21950970463095,"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."}}