{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007550742,0.001992469,0.001544704,0.001649624,0.0005557712,0.002391089,0.00187154,0.002274132,0.002511709],"category_scores_gemma":[0.03503464,0.0006933365,0.001122291,0.001602403,0.001220081,0.002230847,0.00161563,0.002827196,0.001217901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234834,"about_ca_system_score_gemma":0.001516987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002554331,"about_ca_topic_score_gemma":0.002316374,"domain_scores_codex":[0.9950994,0.002558748,0.0003101296,0.0004800984,0.001227773,0.0003239263],"domain_scores_gemma":[0.9857498,0.008414847,0.0009686523,0.002727645,0.001845439,0.0002936151],"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":[0.0001965116,0.0001599785,0.002062761,0.0001665968,0.00008428016,0.00005682919,0.00005013017,0.9612257,0.002003234,0.006006783,0.002724118,0.02526314],"study_design_scores_gemma":[0.00002432506,0.00008252126,0.000298037,0.00002728276,0.000007747015,0.00001955772,0.00001915506,0.9938582,0.002016922,0.002895504,0.0007394736,0.00001128898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3088906,0.002781274,0.6650389,0.001136689,0.0003866644,0.0003437468,0.00128062,0.006805492,0.01333605],"genre_scores_gemma":[0.8188611,0.0005197177,0.1752019,0.0002639127,0.00004719876,0.0004545426,0.002118949,0.0009624045,0.001570255],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007550742,"threshold_uncertainty_score":0.03993267,"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."}}