{"id":"W3159706683","doi":"","title":"Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions","year":2021,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Empirical risk minimization; Regularization (linguistics); Mathematics; Mathematical optimization; Minification; Inference; Computer science; Applied mathematics; Algorithm; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"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":[0.01873043,0.002274941,0.001972354,0.001961825,0.0009131952,0.004071752,0.002729696,0.00312499,0.002075005],"category_scores_gemma":[0.09974302,0.001263503,0.001164889,0.001358273,0.006883034,0.008899196,0.005971637,0.007586544,0.0008248813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00219127,"about_ca_system_score_gemma":0.001319679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0012441,"about_ca_topic_score_gemma":0.0007746026,"domain_scores_codex":[0.9888846,0.004908401,0.0005799577,0.001499182,0.003447974,0.0006798172],"domain_scores_gemma":[0.9113382,0.07331554,0.003742156,0.006474309,0.004152601,0.0009772903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001498502,0.00006935291,0.00114067,0.0003084235,0.00008893497,0.0001814363,0.0002701216,0.2828735,0.002937888,0.6866363,0.002593006,0.02275046],"study_design_scores_gemma":[0.00001049913,0.00005026305,0.0003858673,0.0000779754,0.000009129598,0.00006726151,0.00003046199,0.6677998,0.001010487,0.3294512,0.001078065,0.00002891287],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01787988,0.00276197,0.9696311,0.002378536,0.00009542231,0.00004164857,0.0001839668,0.0002786582,0.006748858],"genre_scores_gemma":[0.6944119,0.007449926,0.2873396,0.002075078,0.00112641,0.000712219,0.0007905199,0.0007546108,0.005339818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01873043,"threshold_uncertainty_score":0.0990572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1087019279839709,"score_gpt":0.3430290848900288,"score_spread":0.234327156906058,"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."}}