{"id":"W2947548407","doi":"10.48550/arxiv.1905.12787","title":"The Theory Behind Overfitting, Cross Validation, Regularization, Bagging, and Boosting: Tutorial","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Overfitting; Boosting (machine learning); Early stopping; Artificial intelligence; AdaBoost; Gradient boosting; Machine learning; Estimator; Mathematics; Support vector machine; Cross-validation; Generalization error; Computer science; Ensemble learning; Regularization (linguistics); Bias of an estimator; Random forest; Algorithm; Statistics; Minimum-variance unbiased estimator; Artificial neural network","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001375344,0.0002739666,0.0002182619,0.000132415,0.0008463709,0.001094577,0.001343212,0.0002537655,0.00002101552],"category_scores_gemma":[0.000631729,0.000264785,0.0001107623,0.0002682106,0.000225378,0.0005542865,0.001606703,0.000581547,0.00005186951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001124153,"about_ca_system_score_gemma":0.0002710668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002528816,"about_ca_topic_score_gemma":0.000004905061,"domain_scores_codex":[0.9978277,0.0004276625,0.0002758683,0.0009537832,0.0001748881,0.000340069],"domain_scores_gemma":[0.9972914,0.0006398641,0.0005134824,0.001061984,0.0003663283,0.0001269517],"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":[0.00004042927,0.00002043515,0.01234562,0.00003455892,0.00006793226,0.00001872546,0.001334969,0.1571612,0.00001468998,0.8272943,0.0004487541,0.001218307],"study_design_scores_gemma":[0.001709205,0.00006049454,0.01111593,0.0001420248,0.0000802867,0.000008379601,0.0003367984,0.6845504,0.0001930349,0.2618413,0.03912302,0.0008391364],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09728309,0.0001372846,0.8918914,0.0001547238,0.003410927,0.0003693633,0.000005126529,0.0002793474,0.006468751],"genre_scores_gemma":[0.9770441,0.0001150188,0.001029631,0.0001184511,0.0003269963,9.81989e-7,0.00002138748,0.00002334111,0.0213201],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8908617,"threshold_uncertainty_score":0.9999804,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04054486057077095,"score_gpt":0.2000192836718457,"score_spread":0.1594744231010747,"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."}}