{"id":"W4286898972","doi":"10.1609/aaai.v37i8.26169","title":"ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-Cost Proxies","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; HEC Montréal","funders":"National Natural Science Foundation of China","keywords":"Computer science; Bayesian optimization; Bayesian probability; Architecture; Task (project management); Generalization; Search cost; Zero (linguistics); Machine learning; Artificial intelligence; Engineering; Mathematics","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":[0.001409091,0.00166539,0.001522512,0.0006827094,0.0005813742,0.001157556,0.002386071,0.001778095,0.006332834],"category_scores_gemma":[0.006034435,0.0008074555,0.0008352826,0.0006972845,0.001074178,0.002027538,0.001683733,0.002846542,0.0019139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001532594,"about_ca_system_score_gemma":0.003647596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01281995,"about_ca_topic_score_gemma":0.02204983,"domain_scores_codex":[0.9990718,0.0002827294,0.00004213819,0.0001835537,0.0002645233,0.0001551517],"domain_scores_gemma":[0.9985974,0.0006715854,0.000117963,0.0001974622,0.000288809,0.0001267818],"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":[0.0002858388,0.0002167528,0.001996265,0.0003160334,0.0001246929,0.00008773705,0.00009794938,0.6952544,0.005801775,0.01639264,0.01332074,0.2661051],"study_design_scores_gemma":[0.00002965813,0.00004297442,0.0001108873,0.00001452651,0.00001407055,0.0000131935,0.00001135091,0.9937553,0.0007632771,0.004227299,0.001010892,0.000006595804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02694045,0.001409967,0.9575557,0.000678338,0.0001418583,0.0001725239,0.0001678813,0.006184389,0.006748891],"genre_scores_gemma":[0.4810207,0.0006619571,0.50584,0.001078194,0.0001237617,0.0005414208,0.0008429314,0.001227447,0.008663579],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01281995,"threshold_uncertainty_score":0.02549064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07634166923046799,"score_gpt":0.3028746530710318,"score_spread":0.2265329838405638,"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."}}