{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002297787,0.0001400315,0.0001715705,0.0001744246,0.0001695812,0.0001965476,0.001064398,0.00005397854,0.00006649529],"category_scores_gemma":[0.0009196106,0.0001246928,0.00006189728,0.001174057,0.00008169172,0.0002099031,0.0004255179,0.000163804,0.000006627119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005899667,"about_ca_system_score_gemma":0.0001251791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002318115,"about_ca_topic_score_gemma":0.0003235747,"domain_scores_codex":[0.9966065,0.002014836,0.0003695138,0.0004233458,0.0003862316,0.0001995506],"domain_scores_gemma":[0.996081,0.0009977533,0.0002156889,0.001454516,0.001192872,0.00005815734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001033097,0.00141899,0.003264008,0.000008146055,0.00001554113,0.000003426942,0.009389168,0.01067085,0.0005963902,0.967625,0.00005377889,0.006944422],"study_design_scores_gemma":[0.001383906,0.000004177803,0.003316266,0.0005810441,0.00001377826,0.000009938698,0.001099107,0.8011668,0.1760248,0.01583508,0.0002502873,0.0003147935],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04210219,0.0001596789,0.9379092,0.002875679,0.00005149858,0.0004624011,0.000002277728,0.0001502856,0.01628672],"genre_scores_gemma":[0.906777,0.00002647136,0.0926412,0.00005694226,0.000002690075,0.0000620743,0.00001346087,0.00001257668,0.0004075631],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9517899,"threshold_uncertainty_score":0.5084825,"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."}}