{"id":"W3196800830","doi":"10.1007/s10915-021-01628-3","title":"Stochastic Gradient Descent with Polyak’s Learning Rate","year":2021,"lang":"en","type":"article","venue":"Journal of Scientific Computing","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Air Force Office of Scientific Research; Fundação para a Ciência e a Tecnologia; Institut de Valorisation des Données","keywords":"Stochastic gradient descent; Subgradient method; Mathematics; Constant (computer programming); Rate of convergence; Generalization; Gradient descent; Regular polygon; Descent (aeronautics); Applied mathematics; Convex function; Mathematical optimization; Convergence (economics); Artificial neural network; Mathematical analysis; Computer science; Artificial intelligence; Geometry","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001804826,0.0001687984,0.0002808562,0.0004244719,0.0005085673,0.0008903057,0.0007614308,0.00003688127,0.00001386229],"category_scores_gemma":[0.0004190676,0.0001398229,0.0001149388,0.001521757,0.0001350672,0.0004642846,0.0003271486,0.0003958033,0.000007046808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000136906,"about_ca_system_score_gemma":0.0004172618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001463931,"about_ca_topic_score_gemma":0.000001353479,"domain_scores_codex":[0.9977054,0.0001681873,0.0006029527,0.0004101444,0.0007170718,0.0003962372],"domain_scores_gemma":[0.9972362,0.0002425058,0.0007175788,0.0003643127,0.001227144,0.000212277],"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":[0.00004928375,0.0005686044,0.002005008,0.00006880247,0.0002109595,0.0009354915,0.006671588,0.8514351,0.01463617,0.04176807,0.001825749,0.07982521],"study_design_scores_gemma":[0.001007627,0.0004543356,0.002243527,0.0007278178,0.00005313085,0.002451489,0.0003951102,0.9792116,0.01030387,0.001999127,0.0007245473,0.0004278625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08944787,0.000208353,0.9081093,0.0004125206,0.001493222,0.00007944539,2.759968e-7,0.0001033928,0.000145587],"genre_scores_gemma":[0.7990718,0.000001588211,0.2005634,0.00005527468,0.00008245339,5.283486e-7,0.000001027038,0.00001110551,0.00021272],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.709624,"threshold_uncertainty_score":0.8585238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01466382442135339,"score_gpt":0.2337888838771633,"score_spread":0.21912505945581,"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."}}