{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008790598,0.0001883851,0.0002460587,0.0001511756,0.0008204657,0.0002732738,0.001224219,0.00007211926,0.00002343752],"category_scores_gemma":[0.0003358697,0.000174717,0.00009175098,0.000126192,0.0001027459,0.0001660073,0.0002717081,0.0003793785,0.00002023444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002876841,"about_ca_system_score_gemma":0.00006879822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003406058,"about_ca_topic_score_gemma":0.00001598638,"domain_scores_codex":[0.9984225,0.0001599166,0.0003113005,0.0004556554,0.0003610006,0.0002896278],"domain_scores_gemma":[0.9980095,0.0001408004,0.0005756723,0.001062518,0.0001125839,0.00009894643],"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":[0.000006069941,0.00006474873,0.02522526,0.00003167851,0.00001351754,0.000004390442,0.0002558941,0.5704937,0.001998224,0.002958967,0.00001662835,0.3989309],"study_design_scores_gemma":[0.0003733943,0.00006995167,0.01248809,0.00003870038,0.000008352923,0.000002929763,0.000005106876,0.9844541,0.001262059,0.0001298094,0.0009829859,0.0001844997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02380304,0.00007116527,0.9715343,0.0006062008,0.0001964085,0.00009690036,0.00000609109,0.0001824249,0.003503487],"genre_scores_gemma":[0.9123327,0.000003834147,0.08738801,0.00004129019,0.00004836518,0.000006747804,0.00003988406,0.00001518436,0.0001239877],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8885297,"threshold_uncertainty_score":0.7124751,"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."}}