{"id":"W2604867865","doi":"10.1007/s10994-017-5683-z","title":"Efficient benchmarking of algorithm configurators via model-based surrogates","year":2017,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft","keywords":"Benchmarking; Computer science; Surrogate model; Range (aeronautics); Algorithm; Set (abstract data type); Configurator; Hyperparameter; Mathematical optimization; Machine learning; Artificial intelligence; Mathematics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00550478,0.001524194,0.00143602,0.001280586,0.000674707,0.002369819,0.002007318,0.002114246,0.003218596],"category_scores_gemma":[0.03331343,0.0005817969,0.0007799259,0.00114173,0.0008401118,0.002255988,0.001501176,0.001871255,0.00085983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001320688,"about_ca_system_score_gemma":0.002069988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001775778,"about_ca_topic_score_gemma":0.002148807,"domain_scores_codex":[0.9955438,0.002776826,0.0002222372,0.0003821507,0.0008060205,0.0002688765],"domain_scores_gemma":[0.9863609,0.008836829,0.0006526763,0.002135201,0.001707955,0.0003064096],"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":[0.0006117782,0.0002459659,0.001641995,0.0001691923,0.00007443266,0.00005944151,0.00004805395,0.920556,0.001824324,0.007683556,0.002568544,0.06451663],"study_design_scores_gemma":[0.00002706105,0.00007462416,0.0001295602,0.00001235073,0.000007309616,0.00001520868,0.00001140803,0.9965773,0.000999278,0.001877219,0.0002639117,0.000004765966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3316518,0.002282927,0.6457222,0.001074624,0.0004311714,0.0003202286,0.0005534168,0.004925067,0.01303852],"genre_scores_gemma":[0.8599715,0.0002112994,0.1373596,0.00009949713,0.00002824327,0.0002170177,0.0006714644,0.0004088535,0.001032597],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00550478,"threshold_uncertainty_score":0.02911246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01398754244513691,"score_gpt":0.2622762930874399,"score_spread":0.248288750642303,"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."}}