{"id":"W2808411657","doi":"10.1101/348557","title":"Hyperparameter-free optimizer of stochastic gradient descent that incorporates unit correction and moment estimation","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Genetics; Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Hyperparameter; Stochastic gradient descent; Benchmark (surveying); Computer science; Gradient descent; Moment (physics); Rate of convergence; Convergence (economics); Artificial intelligence; Mathematical optimization; Artificial neural network; Machine learning; Mathematics; Key (lock)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002532142,0.001381857,0.00162401,0.0006044953,0.0003860058,0.0009371244,0.001312169,0.001635956,0.002124379],"category_scores_gemma":[0.005078957,0.0006608479,0.0008359641,0.0005834042,0.000787729,0.0008476663,0.001037961,0.002057087,0.001005365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007361735,"about_ca_system_score_gemma":0.001376461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00307372,"about_ca_topic_score_gemma":0.002928327,"domain_scores_codex":[0.9992182,0.000348931,0.00007064277,0.0001473949,0.0001589523,0.00005593016],"domain_scores_gemma":[0.9986333,0.0005781172,0.000122514,0.0002078531,0.000375291,0.00008297423],"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":[0.000264662,0.0001234962,0.001459371,0.0001764213,0.000179978,0.0001997358,0.0000866554,0.8122408,0.008439098,0.01485971,0.007930126,0.15404],"study_design_scores_gemma":[0.000008783839,0.00001747811,0.00005690915,0.000005050059,0.000004497617,0.00001178623,0.000001738841,0.9974886,0.001173896,0.0006532503,0.0005731824,0.00000486416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0147935,0.000324775,0.9803771,0.0001995151,0.0001178572,0.00006929541,0.00004554526,0.002382918,0.00168944],"genre_scores_gemma":[0.3296173,0.0001589479,0.6636447,0.0003431174,0.00009645295,0.0002717345,0.0002493724,0.001104285,0.004514023],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00307372,"threshold_uncertainty_score":0.01339138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02284379332564126,"score_gpt":0.2238973574794118,"score_spread":0.2010535641537705,"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."}}