{"id":"W2786615446","doi":"10.48550/arxiv.1803.02021","title":"Understanding Short-Horizon Bias in Stochastic Meta-Optimization","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Horizon; Hyperparameter; Computer science; Benchmark (surveying); Time horizon; Artificial neural network; Optimization problem; Meta learning (computer science); Mathematical optimization; Machine learning; Algorithm; Mathematics; Economics","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":[0.007010039,0.001469401,0.001744093,0.000614082,0.0006792183,0.001764521,0.001887721,0.001996273,0.002275876],"category_scores_gemma":[0.02986877,0.0009836541,0.0007966874,0.0005486029,0.001739783,0.002857529,0.001502965,0.003322597,0.0003421747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001680179,"about_ca_system_score_gemma":0.002570488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002965585,"about_ca_topic_score_gemma":0.004268445,"domain_scores_codex":[0.9983593,0.0009330288,0.00008018706,0.0002419191,0.0002230922,0.0001624193],"domain_scores_gemma":[0.9864457,0.01095291,0.0007896333,0.0009062659,0.0005760159,0.0003295403],"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":[0.00006479826,0.00004929028,0.0009097781,0.0001148507,0.000087988,0.00003927287,0.00003804708,0.9751467,0.0005123035,0.01465209,0.0008403659,0.00754456],"study_design_scores_gemma":[0.00002523901,0.00005236438,0.0001671855,0.00003421561,0.00002183959,0.00001167008,0.00001600735,0.9752923,0.0004042207,0.02332995,0.0006363392,0.000008565689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09233919,0.002570003,0.8944092,0.002757467,0.0002481884,0.0001596457,0.0002332679,0.0008353267,0.006447617],"genre_scores_gemma":[0.8054804,0.0008884301,0.1892864,0.0009554055,0.0001272219,0.0004094756,0.0003282508,0.0004682997,0.002056066],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007010039,"threshold_uncertainty_score":0.03707308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4050751399677809,"score_gpt":0.2476757384022235,"score_spread":0.1573994015655573,"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."}}