{"id":"W2950728319","doi":"10.48550/arxiv.1903.03088","title":"Self-Tuning Networks: Bilevel Optimization of Hyperparameters using\\n Structured Best-Response Functions","year":2019,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Hyperparameter; Hyperparameter optimization; Computer science; Artificial intelligence; Artificial neural network; Machine learning; Mathematical optimization; Algorithm; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002238282,0.002281786,0.001613507,0.0008726024,0.0005406685,0.001789499,0.002313414,0.003349702,0.004118101],"category_scores_gemma":[0.008503568,0.001214409,0.001010436,0.0008943302,0.001883104,0.002577231,0.002104023,0.00341866,0.001403752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001446196,"about_ca_system_score_gemma":0.001507947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004209469,"about_ca_topic_score_gemma":0.004936331,"domain_scores_codex":[0.9990991,0.0004140337,0.0000418525,0.0002208152,0.0001334163,0.0000908173],"domain_scores_gemma":[0.9977958,0.00151781,0.000185994,0.0002029541,0.0002124445,0.00008501406],"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":[0.00003559321,0.00003050767,0.0002152115,0.00003981042,0.00002963678,0.00002598647,0.00003857948,0.9754259,0.0007155729,0.0061798,0.0008458876,0.01641755],"study_design_scores_gemma":[0.000004904922,0.000007538246,0.00001608756,0.00000762528,0.000002247211,0.000003990123,0.000004036787,0.9959986,0.0002099457,0.003575282,0.0001665178,0.000003248873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01602597,0.0003474498,0.9795369,0.000293141,0.00003392227,0.00006214722,0.00005568227,0.0007646346,0.002880239],"genre_scores_gemma":[0.5821978,0.0004703917,0.4065305,0.000753463,0.00009193587,0.0007276254,0.0003745441,0.0008465367,0.008007113],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004209469,"threshold_uncertainty_score":0.01377648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07563503165928508,"score_gpt":0.2103480262418648,"score_spread":0.1347129945825797,"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."}}