{"id":"W2981188016","doi":"10.48550/arxiv.1910.07512","title":"On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Minimax; Mathematical optimization; Convergence (economics); Gradient descent; Mathematics; Optimization problem; Ridge; Computer science; 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":[0.002499265,0.001373886,0.001884554,0.0006673711,0.0007665835,0.0009895707,0.001530699,0.002098236,0.00409127],"category_scores_gemma":[0.007948387,0.000772666,0.0008780223,0.0005816815,0.002320199,0.002214783,0.002727072,0.003317407,0.00122557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007437567,"about_ca_system_score_gemma":0.001338976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00148686,"about_ca_topic_score_gemma":0.001948142,"domain_scores_codex":[0.9991155,0.0004578152,0.00003459739,0.0001416153,0.0001758201,0.0000747065],"domain_scores_gemma":[0.9973286,0.001930265,0.0001761778,0.000255575,0.0002051937,0.0001041108],"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":[0.0001278678,0.0001086427,0.0008111655,0.0002348006,0.00008938734,0.0001560286,0.0001877568,0.7288991,0.003212453,0.1968794,0.005705121,0.06358825],"study_design_scores_gemma":[0.00001866724,0.00005647629,0.00004822797,0.00002274642,0.00000615004,0.00002606375,0.00001228275,0.9492818,0.0004055159,0.04914873,0.0009651023,0.000008151084],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006654985,0.0003985302,0.9877892,0.0005485977,0.00005199626,0.00004349026,0.00001988012,0.0002978955,0.004195503],"genre_scores_gemma":[0.4392625,0.001035629,0.5422291,0.001307767,0.0002655392,0.0006409056,0.0001631829,0.0008667104,0.0142287],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00409127,"threshold_uncertainty_score":0.01368666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05757981876166046,"score_gpt":0.1799677357043652,"score_spread":0.1223879169427048,"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."}}