{"id":"W3035283082","doi":"","title":"Linear Lower Bounds and Conditioning of Differentiable Games","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Game Theory and Applications","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Differentiable function; Upper and lower bounds; Convexity; Mathematics; Saddle point; Leverage (statistics); Complement (music); Regular polygon; Saddle; Convex function; Mathematical optimization; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004163426,0.0001021088,0.0001783389,0.0001053826,0.0001189441,0.0001585268,0.0004174614,0.00003668841,0.004560883],"category_scores_gemma":[0.001404092,0.00008292026,0.0000539618,0.0001698533,0.0001251176,0.0001592349,0.0001243571,0.0002798979,0.0001942758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007404386,"about_ca_system_score_gemma":0.00002543375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000142703,"about_ca_topic_score_gemma":0.000003154344,"domain_scores_codex":[0.9985735,0.000116092,0.0003425902,0.0003050002,0.0005612837,0.0001015567],"domain_scores_gemma":[0.9988305,0.0004534127,0.0002309129,0.0001281561,0.0002688406,0.00008819909],"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":[0.0002416069,0.0001140979,0.051893,0.000009629213,0.00007189846,0.000006081604,0.001561294,0.003906582,0.02742219,0.8949152,0.0005950707,0.01926335],"study_design_scores_gemma":[0.00133914,0.00067289,0.02711469,0.0001135469,0.00002830876,0.00001322711,0.001629408,0.7170057,0.00661876,0.1780659,0.06695464,0.0004437604],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9223749,0.00003455784,0.0206385,0.009642295,0.0001254499,0.00009081409,0.00004720239,0.00005615811,0.04699014],"genre_scores_gemma":[0.9962481,0.00001570487,0.0004599567,0.0004181612,0.00007789757,0.000006359515,0.00002652174,0.0000073366,0.002739937],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7168493,"threshold_uncertainty_score":0.9963491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1142328361906052,"score_gpt":0.3897468339893966,"score_spread":0.2755139977987914,"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."}}