{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001303157,0.0004726158,0.0005933064,0.000253195,0.000262311,0.0004891256,0.002829843,0.0001870464,0.00002015794],"category_scores_gemma":[0.005016195,0.0003662496,0.00009281573,0.0007787906,0.0002511409,0.0002542762,0.001850371,0.0009888936,0.000003933205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007805158,"about_ca_system_score_gemma":0.0002043885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001465846,"about_ca_topic_score_gemma":0.000002385696,"domain_scores_codex":[0.9970382,0.0001093512,0.0007075926,0.001141772,0.0006391233,0.0003640032],"domain_scores_gemma":[0.9964182,0.0006337003,0.0009819008,0.0005528054,0.001215614,0.0001978253],"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":[0.0002372205,0.00004139923,0.00003048844,0.00007288282,0.00004420416,3.875141e-7,0.003126932,0.2794868,0.001214914,0.7087638,0.0000168908,0.006964142],"study_design_scores_gemma":[0.00005252474,0.0003762506,0.00002923682,0.0005481069,0.00004244668,0.000005202968,0.0003844544,0.6475975,0.01184229,0.3387815,0.000002409728,0.0003380977],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001474917,0.00002382051,0.9913579,0.004614535,0.0001594726,0.001477316,0.00001225681,0.0003143719,0.0005654544],"genre_scores_gemma":[0.544778,0.000008323692,0.45458,0.0003852181,0.00003636239,0.0001581672,0.000001323409,0.00002773694,0.00002486203],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5433031,"threshold_uncertainty_score":0.9998789,"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."}}