{"id":"W3214193129","doi":"10.1088/1742-5468/ac98a8","title":"Particle dual averaging: optimization of mean field neural network with global convergence rate analysis*","year":2022,"lang":"en","type":"article","venue":"Journal of Statistical Mechanics Theory and Experiment","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Artificial neural network; Convergence (economics); Rate of convergence; Mathematical optimization; Nonlinear system; Empirical risk minimization; Computer science; Inner loop; Applied mathematics; Mathematics; Artificial intelligence; Physics; Key (lock)","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":[0.001897188,0.0006989131,0.00112027,0.0004916459,0.0003946027,0.0008706445,0.001179233,0.001075484,0.001228433],"category_scores_gemma":[0.004350161,0.0004516601,0.0005609617,0.0004579131,0.001168847,0.001349959,0.001598918,0.001206323,0.0001876939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008823058,"about_ca_system_score_gemma":0.001093158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002210887,"about_ca_topic_score_gemma":0.001265122,"domain_scores_codex":[0.999522,0.0001944122,0.00001984289,0.00008562728,0.0001313379,0.0000468315],"domain_scores_gemma":[0.9988638,0.0006126305,0.0001243545,0.00009367022,0.0002289245,0.00007657297],"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":[0.00006017537,0.0000316139,0.0004375104,0.00006174697,0.00004934235,0.00004464866,0.00003114079,0.9094111,0.002634932,0.06212514,0.001127283,0.02398534],"study_design_scores_gemma":[0.000001470396,0.000004604593,0.0000130436,7.908316e-7,9.989566e-7,0.000002223607,4.868995e-7,0.9967359,0.0001155693,0.003054629,0.00006907874,0.00000123119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01154197,0.0001445787,0.9866523,0.0002078792,0.00004729721,0.00001566267,0.00001527774,0.000102114,0.001272937],"genre_scores_gemma":[0.6738228,0.0003068181,0.3202938,0.0002771932,0.0001665963,0.000180392,0.0001097419,0.0002194556,0.004623212],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002210887,"threshold_uncertainty_score":0.01003337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01051598684742822,"score_gpt":0.2586346660308372,"score_spread":0.248118679183409,"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."}}