{"id":"W2166107799","doi":"10.1162/089976600300015187","title":"Gradient-Based Optimization of Hyperparameters","year":2000,"lang":"en","type":"article","venue":"Neural Computation","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":478,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Hyperparameter; Cholesky decomposition; Gradient descent; Hyperparameter optimization; Computer science; Selection (genetic algorithm); Mathematics; Mathematical optimization; Model selection; Applied mathematics; Computation; Quadratic equation; Artificial intelligence; Algorithm; Machine learning; Artificial neural network; Support vector machine","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":[],"consensus_categories":[],"category_scores_codex":[0.00001502044,0.00005651255,0.00006851542,0.00005022164,0.00001585258,0.000009284764,0.00003590442,0.00002382857,0.00002929384],"category_scores_gemma":[0.000002412878,0.00005941313,0.00002657251,0.0001023084,0.00001403498,0.00005507721,0.000001810967,0.00003584936,0.000003408782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001086307,"about_ca_system_score_gemma":0.000002205693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006641528,"about_ca_topic_score_gemma":3.877905e-7,"domain_scores_codex":[0.9996894,0.00001401631,0.0001045236,0.00006140354,0.00006666257,0.00006400901],"domain_scores_gemma":[0.9998633,0.00002212413,0.00001585858,0.00005872261,0.00002444627,0.00001549402],"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":[0.000005534419,0.000005819721,0.00004297088,0.00000439232,0.000002691198,7.198624e-7,0.00001775245,0.9583919,0.00144334,0.000005478183,0.0001606237,0.03991874],"study_design_scores_gemma":[0.0001089895,0.00003580642,0.0004803102,0.00001247525,0.000005359617,0.000001622965,0.000001893274,0.9812471,0.0179351,0.00007752127,0.00003826709,0.00005561062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8060521,0.00002516447,0.1925844,0.00001650352,0.00006863565,0.00006439186,0.000001093646,0.0003522861,0.0008354516],"genre_scores_gemma":[0.9771938,0.000004952242,0.02271366,0.00004074216,0.00001153553,0.00000186494,0.00001868594,0.00001070033,0.000004039061],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1711417,"threshold_uncertainty_score":0.2422797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01406182111473949,"score_gpt":0.2205749250895469,"score_spread":0.2065131039748074,"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."}}