{"id":"W2895642264","doi":"10.1007/978-3-030-01424-7_39","title":"Width of Minima Reached by Stochastic Gradient Descent is Influenced by Learning Rate to Batch Size Ratio","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"Institut de Valorisation des Données; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; European Commission","keywords":"Maxima and minima; Stochastic gradient descent; Generalization; Computer science; Range (aeronautics); Convergence (economics); Gradient descent; Artificial neural network; Rate of convergence; Generalization error; Set (abstract data type); Artificial intelligence; Key (lock); Algorithm; Applied mathematics; Mathematics; Mathematical analysis; Materials science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.005315804,0.001016885,0.00145173,0.001279786,0.0007034246,0.002526814,0.001989008,0.002389651,0.005447706],"category_scores_gemma":[0.05735023,0.0009138711,0.0007234204,0.0008347975,0.001344339,0.004070258,0.00213066,0.003491853,0.001830288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000811473,"about_ca_system_score_gemma":0.001217418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009720807,"about_ca_topic_score_gemma":0.001122164,"domain_scores_codex":[0.9984081,0.0004531046,0.0001145423,0.0004304663,0.0003397458,0.0002540556],"domain_scores_gemma":[0.965113,0.02700641,0.001465537,0.002094982,0.002868988,0.001451037],"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":[0.002723453,0.0004368424,0.01088236,0.000891947,0.0003279962,0.0005571597,0.0007517507,0.6439437,0.09149129,0.07377293,0.01352672,0.1606938],"study_design_scores_gemma":[0.00003720469,0.000180403,0.002186545,0.00008095567,0.00005563651,0.0001584577,0.0000747325,0.9570082,0.01446125,0.0247318,0.0009815915,0.00004316388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2667659,0.003364748,0.7090677,0.001694114,0.0005155245,0.00009544678,0.0005342307,0.003159326,0.01480303],"genre_scores_gemma":[0.8861479,0.001242247,0.09972044,0.0003859822,0.0001838445,0.0001583124,0.0005341413,0.003409843,0.008217331],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005447706,"threshold_uncertainty_score":0.02811301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01114941303387985,"score_gpt":0.2411353598657182,"score_spread":0.2299859468318383,"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."}}