{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001056889,0.00009528713,0.0002363053,0.00005364585,0.0001320008,0.00003700433,0.0002230324,0.00001776916,0.0001516217],"category_scores_gemma":[0.0000913815,0.00007912115,0.00004478219,0.0004902388,0.0000310789,0.0001442984,0.0001754272,0.0001091427,1.086421e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000475264,"about_ca_system_score_gemma":0.00004137362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003066667,"about_ca_topic_score_gemma":2.72648e-7,"domain_scores_codex":[0.9986211,0.0003493181,0.0003856686,0.0001550057,0.0003296093,0.0001593136],"domain_scores_gemma":[0.9988768,0.0004292018,0.0003094816,0.0001524183,0.0001225939,0.000109503],"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":[0.0002273579,0.00006033575,0.00004730955,0.000002486855,0.00009017604,0.00001956994,0.0003712197,0.360074,0.00006486641,0.638592,0.00003275212,0.0004179339],"study_design_scores_gemma":[0.0003367034,0.001726662,0.00002073919,0.000007872843,0.0001071627,0.00005971888,0.0002763686,0.9040448,0.001722699,0.09159782,0.000007743043,0.00009169732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00491876,0.0001509691,0.9944596,0.0001612147,0.0001841166,0.00008539127,0.00000782643,0.00001689605,0.00001528076],"genre_scores_gemma":[0.7264835,0.000009164872,0.2733314,0.0001504917,0.00001251731,0.000005961961,0.000001237211,0.000003011855,0.000002715849],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7215647,"threshold_uncertainty_score":0.3226467,"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."}}