{"id":"W2296059279","doi":"10.1609/aaai.v29i1.9375","title":"Efficient Benchmarking of Hyperparameter Optimizers via Surrogates","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Deutsche Forschungsgemeinschaft","keywords":"Hyperparameter; Hyperparameter optimization; Machine learning; Computer science; Artificial intelligence; Benchmarking; Regression; Algorithm; Support vector machine; Mathematics; Statistics","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":[0.0009358811,0.0001703651,0.0002435682,0.0001393228,0.00009133948,0.0001238778,0.001660093,0.0000694512,0.00002101288],"category_scores_gemma":[0.0006530402,0.0001244698,0.00009405311,0.0006010922,0.0002397324,0.0001678078,0.0003555384,0.0002307977,0.00004351112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003737729,"about_ca_system_score_gemma":0.00009373601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009363394,"about_ca_topic_score_gemma":0.000004012429,"domain_scores_codex":[0.9982487,0.00003195002,0.000512542,0.0004073375,0.0005537784,0.0002456784],"domain_scores_gemma":[0.9981665,0.0001248162,0.0005020026,0.0003743677,0.0007267136,0.0001055996],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001131449,0.0002629792,0.001791605,0.00006091316,0.00002541751,3.129235e-7,0.003650097,0.007772421,0.04490424,0.7940158,0.0001563948,0.1472467],"study_design_scores_gemma":[0.00003558059,0.0002010462,0.0003123296,0.000114672,0.00001038138,0.000003686107,0.000383082,0.7691275,0.2097301,0.019866,0.00006149655,0.0001540157],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6821634,0.00005167894,0.2883275,0.004196588,0.001030259,0.0005544879,0.000007563617,0.0001629757,0.0235056],"genre_scores_gemma":[0.9795278,0.00000609329,0.02030265,0.00005251898,0.00003572595,0.0000101281,0.000001004636,0.00000758482,0.00005646035],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7741498,"threshold_uncertainty_score":0.5075731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09360323200453574,"score_gpt":0.298169570383572,"score_spread":0.2045663383790363,"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."}}