{"id":"W2948831929","doi":"10.1609/aaai.v34i04.5727","title":"A Stochastic Derivative-Free Optimization Method with Importance Sampling: Theory and Learning to Control","year":2020,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"King Abdullah University of Science and Technology","keywords":"Sampling (signal processing); Mathematical optimization; Computer science; Convergence (economics); Convex function; Function (biology); Derivative (finance); Regular polygon; Sample (material); Derivative-free optimization; Acceleration; Minification; Convex optimization; Control (management); Algorithm; Mathematics; Optimization problem; Artificial intelligence","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":[0.002234692,0.001175939,0.001520316,0.0007811267,0.0004788148,0.001075431,0.001792282,0.001789957,0.002442228],"category_scores_gemma":[0.006425536,0.0006913333,0.0009578482,0.0008274296,0.001650966,0.001467693,0.001574432,0.00239214,0.0004480467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000981883,"about_ca_system_score_gemma":0.001419799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002925885,"about_ca_topic_score_gemma":0.001972513,"domain_scores_codex":[0.9990727,0.0003568061,0.00003415922,0.0001516472,0.0003236325,0.000061135],"domain_scores_gemma":[0.9982285,0.001191788,0.0001059469,0.0001286384,0.00025734,0.00008776848],"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":[0.00007003862,0.00006846048,0.000352833,0.0001694546,0.0000524533,0.00008256895,0.00005966704,0.865355,0.002515509,0.06078812,0.002105067,0.06838094],"study_design_scores_gemma":[0.000005958989,0.00001569476,0.00002254499,0.000005631279,0.000002453926,0.000009313132,0.000001308549,0.9948117,0.0002547461,0.004487492,0.0003793843,0.000003881651],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009958617,0.0001273836,0.9981411,0.00009806541,0.00003201417,0.00001811107,0.000006365414,0.00006781072,0.0005133397],"genre_scores_gemma":[0.2778983,0.0006010873,0.7147542,0.0003685256,0.0002839204,0.0003981793,0.0001001264,0.0002480248,0.005347602],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002925885,"threshold_uncertainty_score":0.01181835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07210470146840367,"score_gpt":0.3162483920210044,"score_spread":0.2441436905526007,"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."}}