{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003612151,0.0004175942,0.0003633522,0.0004108929,0.0002292328,0.0002565094,0.002861116,0.0003533805,0.0000210176],"category_scores_gemma":[0.0001185613,0.0004067351,0.0002490185,0.000837515,0.000119634,0.0003406515,0.001979424,0.0006250897,0.00006503882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003100823,"about_ca_system_score_gemma":0.0002332393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000346434,"about_ca_topic_score_gemma":0.000001595914,"domain_scores_codex":[0.9975592,0.0001646765,0.0002726795,0.001386053,0.0002074842,0.0004098785],"domain_scores_gemma":[0.9969852,0.0002496393,0.0003910055,0.002008915,0.0002403616,0.0001248841],"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":[0.00001573518,0.00007524327,0.0000558386,0.00003099743,0.00003922082,0.00001449265,0.0001550415,0.7542738,0.000001349033,0.2444417,0.0008007229,0.00009585411],"study_design_scores_gemma":[0.0003885665,0.00009052055,0.00002968292,0.0001070952,0.0000476847,0.000004283471,0.00003254946,0.9848799,0.00004115933,0.01390085,0.0000509732,0.0004267421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001804705,0.00002841442,0.9864745,0.0001245745,0.0006855825,0.0009160143,0.00001102618,0.0006751596,0.009280025],"genre_scores_gemma":[0.8799562,0.00005353313,0.1181334,0.0003046709,0.000052253,0.000008113682,0.0000544199,0.00004076698,0.001396593],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8781515,"threshold_uncertainty_score":0.9998385,"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."}}