{"id":"W4200632679","doi":"10.1609/aaai.v36i4.20301","title":"Sample Average Approximation for Stochastic Optimization with Dependent Data: Performance Guarantees and Tractability","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; Huawei Technologies (Canada); University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Estimator; Stochastic approximation; Stochastic optimization; Stochastic gradient descent; Bounded function; Iterated function; Mathematics; Applied mathematics; Mathematical optimization; Monotone polygon; Asymptotically optimal algorithm; Consistency (knowledge bases); Computer science; Discrete mathematics; Artificial neural network; Mathematical analysis; Artificial intelligence; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0007374734,0.0001624655,0.0001825931,0.0001167431,0.0004581527,0.0001743996,0.001579994,0.00003212114,0.00002379864],"category_scores_gemma":[0.0004500675,0.0001279476,0.0000265384,0.0004289731,0.0001511027,0.0007189955,0.0006280406,0.0001750551,5.195209e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006013087,"about_ca_system_score_gemma":0.0000820034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001729911,"about_ca_topic_score_gemma":0.000002301357,"domain_scores_codex":[0.9983625,0.00001741365,0.0003788149,0.0005561975,0.0004750398,0.0002100321],"domain_scores_gemma":[0.9985565,0.0002034203,0.0003712272,0.0004075329,0.000419347,0.00004198607],"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":[0.000270294,0.000272001,0.0001669862,0.0001080752,0.00001812593,7.238988e-8,0.001865145,0.3414111,0.001082483,0.6209396,0.00002204046,0.03384401],"study_design_scores_gemma":[0.00005049569,0.0004321285,0.00004445475,0.0000439888,0.00001269943,0.00000754753,0.0002755218,0.9577287,0.01550137,0.02575099,0.000004024157,0.0001480077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02406846,0.000007929089,0.9738654,0.0006466421,0.0001182711,0.001026643,0.00004874394,0.00009805857,0.0001198676],"genre_scores_gemma":[0.8775907,0.000006752118,0.1221049,0.00004965268,0.00001390855,0.0002018206,0.000009346708,0.00000979494,0.00001316023],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8535222,"threshold_uncertainty_score":0.5217553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07742442528774132,"score_gpt":0.2772157989378486,"score_spread":0.1997913736501073,"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."}}