{"id":"W2995291884","doi":"","title":"On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Minimax; Mathematical optimization; Convergence (economics); Gradient descent; Optimization problem; Computer science; Mathematics; Artificial intelligence; Artificial neural network","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":[0.002471987,0.001301906,0.00205332,0.0006418698,0.0007054039,0.0009383641,0.001637926,0.002090576,0.003770327],"category_scores_gemma":[0.006949699,0.0007704822,0.0009347555,0.0006045498,0.002047616,0.002243735,0.002577999,0.003072939,0.001152431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006792238,"about_ca_system_score_gemma":0.001342067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001472986,"about_ca_topic_score_gemma":0.002066458,"domain_scores_codex":[0.9991731,0.0004143677,0.00003344487,0.0001385388,0.0001648393,0.00007567622],"domain_scores_gemma":[0.9976175,0.001664064,0.0001616842,0.000248399,0.0002091573,0.00009902862],"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":[0.0001209412,0.0001127804,0.0008519823,0.0002147292,0.0000898106,0.0001607431,0.0001902709,0.7750995,0.003129507,0.140775,0.004915725,0.07433911],"study_design_scores_gemma":[0.00001554415,0.00005513547,0.00004497288,0.00001912921,0.000006002134,0.00003074246,0.00001160196,0.9674944,0.0003765194,0.03111525,0.0008230974,0.00000749947],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006154044,0.0003913133,0.9897442,0.0003806731,0.00004364647,0.00003978227,0.00001580906,0.0003245413,0.002905884],"genre_scores_gemma":[0.4170362,0.0009272269,0.5683541,0.001116469,0.0002124348,0.000572884,0.0001543535,0.0007812312,0.01084518],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003770327,"threshold_uncertainty_score":0.01307327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06320326867818603,"score_gpt":0.3032700120988561,"score_spread":0.2400667434206701,"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."}}