{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006934313,0.0005930611,0.000635374,0.0007020175,0.0001972497,0.0003246983,0.001282861,0.0003805038,0.000009510964],"category_scores_gemma":[0.0003799247,0.0006292506,0.0001080372,0.0007048461,0.0003416099,0.0004093636,0.001671592,0.0004197978,0.000008325319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003050464,"about_ca_system_score_gemma":0.0003032895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004215189,"about_ca_topic_score_gemma":0.000001030673,"domain_scores_codex":[0.9969138,0.0001531846,0.0007005353,0.001148878,0.0006315631,0.0004520318],"domain_scores_gemma":[0.9956383,0.0001563269,0.001032545,0.002073881,0.0008291687,0.0002698345],"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":[0.0008110614,0.006295134,0.02083388,0.005622266,0.002948871,0.0001725237,0.001512915,0.6466145,0.1684489,0.1331399,0.01273394,0.0008661236],"study_design_scores_gemma":[0.0006944179,0.000312158,0.007055553,0.0009474964,0.0001366103,2.24464e-7,0.000003281021,0.8725068,0.1170618,0.0003674706,0.00003039803,0.0008837433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09987178,0.0002295491,0.8958713,0.0001384177,0.00212782,0.001080046,0.00004437082,0.0006323939,0.000004280595],"genre_scores_gemma":[0.6491726,0.00004055814,0.3504449,0.00003476864,0.00005445492,0.0001991564,5.542091e-7,0.00005019213,0.000002884901],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5493008,"threshold_uncertainty_score":0.9996159,"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."}}