{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006144039,0.000225178,0.000199936,0.0002255005,0.0004038022,0.0005480833,0.001657687,0.00007582892,0.00002366926],"category_scores_gemma":[0.0003111792,0.0001511787,0.0000556497,0.001590515,0.0001647812,0.00052973,0.0003572924,0.0004805355,0.00004437563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002979474,"about_ca_system_score_gemma":0.00009420914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000443284,"about_ca_topic_score_gemma":0.00001052291,"domain_scores_codex":[0.9979615,0.00004364201,0.0003958008,0.0005816005,0.000621295,0.0003961976],"domain_scores_gemma":[0.9986328,0.00009355116,0.0002907271,0.0003730203,0.000522025,0.00008786559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001395564,0.0001090109,0.002078274,0.0001530159,0.00002332917,0.000001622236,0.004500129,0.09426767,0.03022159,0.434129,0.0001343764,0.4342424],"study_design_scores_gemma":[0.00002773637,0.0001834298,0.0004704823,0.0001252615,0.000005912079,0.000007969348,0.0002475581,0.9123782,0.07692108,0.009412603,0.00003628512,0.000183474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03923796,0.000005588323,0.9441179,0.01139146,0.0001816119,0.0009780194,0.000005430134,0.0004471954,0.003634848],"genre_scores_gemma":[0.9779484,0.00000971778,0.02155181,0.00009660074,0.0000569822,0.00007270887,0.000007518787,0.00001813954,0.0002381161],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9387105,"threshold_uncertainty_score":0.6164889,"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."}}