{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005054307,0.0009040667,0.0009914563,0.0007816457,0.0006626144,0.0001777817,0.002924062,0.0007565773,0.0000740266],"category_scores_gemma":[0.0001154867,0.001156234,0.0005567719,0.003692864,0.000431853,0.001195877,0.002629715,0.001180712,0.00005220387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007874219,"about_ca_system_score_gemma":0.0007710654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005531933,"about_ca_topic_score_gemma":0.000009211645,"domain_scores_codex":[0.99454,0.0008102734,0.0008995538,0.002571487,0.000265607,0.0009130712],"domain_scores_gemma":[0.9925552,0.001068031,0.001756043,0.003376137,0.0008408094,0.0004037837],"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":[0.0004999815,0.0002357189,0.001013129,0.00007443001,0.0002626446,0.00002718386,0.0002168197,0.9924935,0.0003339133,0.003776662,0.00002344849,0.001042556],"study_design_scores_gemma":[0.0009936815,0.000240434,0.0002448832,0.0002820039,0.0005098084,0.00002550485,0.0001646677,0.9946417,0.0001098385,0.001477511,0.0003232725,0.0009866907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1579321,0.0001223337,0.8382595,0.00004486131,0.001332334,0.001898713,0.00005913071,0.0002490024,0.0001019691],"genre_scores_gemma":[0.8151879,0.0004397824,0.1834286,0.0000622883,0.0001177265,0.000006588951,0.00004065569,0.00007717508,0.0006392623],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6572558,"threshold_uncertainty_score":0.9990888,"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."}}