{"id":"W2983785293","doi":"10.48550/arxiv.1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Hyperparameter; Hessian matrix; Computer science; Function (biology); Inverse; Hyperparameter optimization; Machine learning; Artificial intelligence; Algorithm; Mathematical optimization; Mathematics; Applied mathematics","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":[0.0001448788,0.0001942093,0.0002657097,0.0002217035,0.00007665616,0.00007572491,0.001283977,0.0001912622,0.00001308077],"category_scores_gemma":[0.00003588948,0.0002195107,0.0001417865,0.0003331947,0.00004241919,0.0002637426,0.0009332492,0.0003892477,0.00004407478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000087232,"about_ca_system_score_gemma":0.00006886472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002063052,"about_ca_topic_score_gemma":0.000005184018,"domain_scores_codex":[0.9986436,0.0001319485,0.0001949914,0.0007509306,0.00008550655,0.0001929907],"domain_scores_gemma":[0.9980671,0.0001166288,0.0003891044,0.00125966,0.00009135315,0.00007614668],"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":[0.00003902906,0.000307072,0.02121411,0.000313812,0.0002393215,0.00001122059,0.0007087921,0.7921529,0.006828717,0.1706071,0.002743501,0.004834401],"study_design_scores_gemma":[0.0002860159,0.00003998922,0.005078377,0.00006341129,0.00005435087,9.469245e-7,0.00003480172,0.9904968,0.0005033895,0.002564828,0.0005911249,0.0002860175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.260851,0.00005034733,0.737573,0.00009601721,0.0002613629,0.0001444255,0.00003988274,0.00009897463,0.0008850644],"genre_scores_gemma":[0.9946408,0.0001498215,0.004260821,0.00003369653,0.00001417006,6.493237e-7,0.0002084208,0.00001112443,0.0006804424],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7337899,"threshold_uncertainty_score":0.8951387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04998806090801263,"score_gpt":0.1933354099792792,"score_spread":0.1433473490712665,"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."}}