{"id":"W4391131725","doi":"10.1145/3594234","title":"Optimistic Rates: A Unifying Theory for Interpolation Learning and Regularization in Linear Regression","year":2024,"lang":"en","type":"article","venue":"ACM / IMS Journal of Data Science","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regularization (linguistics); Linear regression; Mathematics; Interpolation (computer graphics); Econometrics; Applied mathematics; Linear interpolation; Bayesian multivariate linear regression; Regression; Proper linear model; Statistics; Linear model; Computer science; Artificial intelligence; Mathematical analysis","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":[0.02702484,0.003135378,0.002592654,0.0030353,0.001554827,0.004173131,0.005226982,0.003304289,0.005379873],"category_scores_gemma":[0.09292123,0.001441769,0.002736032,0.001924806,0.006600928,0.009626208,0.009719738,0.01101625,0.001381421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002697215,"about_ca_system_score_gemma":0.00209145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001312398,"about_ca_topic_score_gemma":0.0008099982,"domain_scores_codex":[0.9887251,0.005737596,0.0004366834,0.001330976,0.00300019,0.0007694336],"domain_scores_gemma":[0.9365482,0.04790811,0.00415056,0.006307133,0.003672892,0.001413154],"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":[0.0001396532,0.0000459381,0.001194962,0.0002433347,0.00007606363,0.0001427677,0.0003008224,0.0858565,0.001260253,0.8897017,0.002208852,0.01882906],"study_design_scores_gemma":[0.00002755958,0.0001636728,0.0003466374,0.0002045939,0.00004155349,0.0001882682,0.00006540381,0.4158763,0.001381079,0.577021,0.004622264,0.00006169802],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005180027,0.001258133,0.9876061,0.001021533,0.0001174192,0.00005144137,0.00008188259,0.0001561007,0.004527268],"genre_scores_gemma":[0.5662119,0.007563984,0.4017983,0.003079698,0.002235388,0.001066694,0.0005524984,0.001261314,0.01623026],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02702484,"threshold_uncertainty_score":0.1429228,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0531062436633936,"score_gpt":0.3582758260044411,"score_spread":0.3051695823410475,"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."}}