{"id":"W2955301088","doi":"10.1109/ccgrid.2019.00092","title":"A Performance Improvement Approach for Second-Order Optimization in Large Mini-batch Training","year":2019,"lang":"en","type":"article","venue":"","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Core Research for Evolutional Science and Technology; Canadian Institute for Advanced Research; Nvidia","keywords":"Overfitting; Computer science; Generalization; Regularization (linguistics); Artificial intelligence; Smoothing; Artificial neural network; Deep learning; Training (meteorology); Deep neural networks; Training set; Machine learning; Algorithm; Mathematical optimization; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.000593291,0.00009466906,0.0001240664,0.000122944,0.0000368962,0.00008515344,0.0003262204,0.00006288781,0.00008071621],"category_scores_gemma":[0.000009178299,0.00008773339,0.00002849658,0.0002950574,0.000005770652,0.000606013,0.00007609464,0.00007785969,0.000006680312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003187254,"about_ca_system_score_gemma":0.00007106711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003238961,"about_ca_topic_score_gemma":0.000007389068,"domain_scores_codex":[0.9990989,0.00002055717,0.0002171076,0.000302658,0.0001270798,0.0002337199],"domain_scores_gemma":[0.9995298,0.0000305074,0.00006380341,0.0002748245,0.00007213418,0.00002890521],"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":[0.0001234613,0.001689919,0.01433944,0.0007901877,0.00008809293,0.000001412565,0.07832472,0.3907526,0.007399808,0.3190455,0.004337971,0.1831069],"study_design_scores_gemma":[0.0006329386,0.0001638234,0.0002179249,0.000005966369,7.302841e-7,8.261711e-7,0.0002625576,0.9945071,0.002973496,0.0001009399,0.001004653,0.0001290054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05430331,0.000004409205,0.9263132,0.0001729272,0.00005243373,0.0007328563,0.000001395554,0.000170988,0.01824847],"genre_scores_gemma":[0.4645991,0.000001437442,0.5330813,0.0006654246,0.000008314033,0.0001189361,0.0000111568,0.000006022288,0.001508309],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6037546,"threshold_uncertainty_score":0.3577664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01947409969596551,"score_gpt":0.2522402888070221,"score_spread":0.2327661891110566,"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."}}