{"id":"W2808399504","doi":"10.48550/arxiv.1806.04613","title":"Improving Regression Performance with Distributional Losses","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Overfitting; Regression; Ambiguity; Computer science; Generalization; Machine learning; Artificial intelligence; Reinforcement learning; Statistics; Mathematics; Artificial neural network","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":[0.0002068749,0.0002187177,0.0001631882,0.0001166296,0.0002863598,0.0001516271,0.001264898,0.000154665,0.00002386536],"category_scores_gemma":[0.00003946113,0.0001888275,0.00005424602,0.0003389238,0.0001375416,0.0005006585,0.001217304,0.0004697843,0.00009357316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001383357,"about_ca_system_score_gemma":0.0002361544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008263808,"about_ca_topic_score_gemma":0.000009997155,"domain_scores_codex":[0.998561,0.00008157775,0.0001189747,0.000887539,0.0001161283,0.0002347814],"domain_scores_gemma":[0.9982518,0.00004786679,0.0002968902,0.001109614,0.0001912256,0.0001025931],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005295947,0.0005783864,0.3911458,0.001153268,0.0002516702,0.0004026225,0.0004756503,0.110991,0.0004270708,0.437794,0.005324682,0.05092624],"study_design_scores_gemma":[0.000295398,0.0001185997,0.03430319,0.0002172573,0.00002987247,0.00001138568,0.00001252436,0.9608119,0.0002500932,0.001551611,0.002023133,0.0003750944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3412758,0.00001765432,0.6570906,0.0001098394,0.0001863665,0.00008596558,0.00001982681,0.0001944544,0.001019542],"genre_scores_gemma":[0.9946798,0.00005521477,0.003985528,0.00002501749,0.0001111747,8.032763e-7,0.000201359,0.00000903116,0.0009320441],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8498209,"threshold_uncertainty_score":0.7700161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04654616556887559,"score_gpt":0.1877857698074328,"score_spread":0.1412396042385572,"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."}}