{"id":"W3041060701","doi":"10.48550/arxiv.2007.05477","title":"Exponential Convergence of Gradient Methods in Concave Network Zero-sum Games","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Zero-sum game; Zero (linguistics); Lipschitz continuity; Generalization; Convergence (economics); Mathematics; Nash equilibrium; Regular polygon; Fictitious play; Applied mathematics; Mathematical optimization; Mathematical economics; Pure mathematics; Mathematical analysis","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":[0.002958599,0.0004097156,0.001092569,0.0006231275,0.0001082077,0.00008359731,0.002862156,0.0003833607,0.0006577493],"category_scores_gemma":[0.001907752,0.0004144883,0.000444283,0.002600016,0.0006705833,0.0003079417,0.003606486,0.001197127,0.0001579813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002769211,"about_ca_system_score_gemma":0.0004103924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000234725,"about_ca_topic_score_gemma":0.00009971948,"domain_scores_codex":[0.994219,0.001540035,0.0009352211,0.001911527,0.0006887144,0.000705514],"domain_scores_gemma":[0.9945036,0.002277507,0.0008131146,0.001454816,0.0005835278,0.0003674666],"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":[0.000446596,0.0001410293,0.01540902,0.00006926383,0.0001415054,0.0008043414,0.0007451292,0.960202,0.0003982789,0.01264886,0.00264998,0.006344029],"study_design_scores_gemma":[0.001160133,0.0001607754,0.009594063,0.000138945,0.00006056016,0.0000036577,0.0008969449,0.5047227,0.002074789,0.4771149,0.003411478,0.0006611012],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1134849,0.0002770205,0.8831278,0.0001153714,0.001490046,0.0005618619,0.00005607194,0.00005425434,0.0008326526],"genre_scores_gemma":[0.9827068,0.0004034549,0.01513646,0.00004378779,0.000148997,0.000002770417,0.00001492722,0.00002922022,0.001513535],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8692219,"threshold_uncertainty_score":0.9998307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3396832296260758,"score_gpt":0.3713927499233881,"score_spread":0.03170952029731233,"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."}}