{"id":"W3214140707","doi":"","title":"On the Role of Optimization in Double Descent: A Least Squares Study","year":2021,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"DeepMind; Engineering and Physical Sciences Research Council; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Overfitting; Gradient descent; Moore–Penrose pseudoinverse; Least-squares function approximation; Covariance matrix; Covariance; Mathematics; Generalization; Mathematical optimization; Applied mathematics; Computer science; Matrix (chemical analysis); Artificial neural network; Algorithm; Inverse; Artificial intelligence; Statistics; Mathematical analysis","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":[0.007017482,0.001577915,0.001406054,0.001096764,0.0005480985,0.001766833,0.001440227,0.002214868,0.00293318],"category_scores_gemma":[0.05074471,0.0008117491,0.001315727,0.0007636633,0.004028908,0.004704736,0.003057334,0.00399064,0.0007278011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007778918,"about_ca_system_score_gemma":0.0007810005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001650232,"about_ca_topic_score_gemma":0.0007966248,"domain_scores_codex":[0.9975414,0.001218569,0.0001102572,0.0003744058,0.0006018755,0.0001535187],"domain_scores_gemma":[0.9752431,0.01950989,0.00124735,0.001842563,0.001620026,0.0005370892],"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":[0.000272722,0.0001596265,0.003991127,0.0005592543,0.0001905345,0.0006060658,0.0006657375,0.4593583,0.01009733,0.4463419,0.003987549,0.07376992],"study_design_scores_gemma":[0.00001322002,0.0001357937,0.0007237653,0.00008153744,0.00001422006,0.0001151364,0.00004790981,0.9095588,0.001959171,0.08584218,0.001478104,0.0000301376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04749593,0.002344842,0.9399139,0.002188223,0.0001008298,0.00003858789,0.00004605233,0.0003762793,0.007495315],"genre_scores_gemma":[0.8047216,0.00254857,0.1802755,0.0009101837,0.0003267268,0.000150651,0.0001476193,0.001111131,0.00980797],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007017482,"threshold_uncertainty_score":0.03711241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01247180139124885,"score_gpt":0.218450882909433,"score_spread":0.2059790815181842,"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."}}