{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00212922,0.001999486,0.001481254,0.001129637,0.0006942499,0.001744623,0.002568623,0.001772772,0.005972149],"category_scores_gemma":[0.01262147,0.001147193,0.0008797542,0.001210907,0.001506831,0.003208262,0.002632388,0.00358195,0.004109391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001309013,"about_ca_system_score_gemma":0.002159944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003525671,"about_ca_topic_score_gemma":0.005846279,"domain_scores_codex":[0.998716,0.0003837099,0.00008305814,0.0002746103,0.0004384381,0.0001041273],"domain_scores_gemma":[0.9971249,0.001520402,0.0002303774,0.0006186982,0.0004123837,0.00009337419],"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":[0.0001958526,0.0001065172,0.00160754,0.0001637497,0.0001164988,0.0001203122,0.0001919104,0.5257918,0.007748331,0.04901979,0.009342404,0.4055953],"study_design_scores_gemma":[0.00003041538,0.00002447058,0.00009799121,0.00001783032,0.00001114553,0.00003796806,0.00001482582,0.9600285,0.001985966,0.03500585,0.002732076,0.00001300236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005624327,0.0001483192,0.9905229,0.0002000026,0.00004120632,0.00004260376,0.00004466007,0.001515375,0.001860566],"genre_scores_gemma":[0.1474187,0.0001666662,0.8450739,0.0003599098,0.00008132545,0.0003523682,0.000274794,0.001062762,0.005209676],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005972149,"threshold_uncertainty_score":0.01997882,"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."}}