{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006829215,0.002014341,0.001708816,0.0009965175,0.0005625386,0.001927981,0.001981295,0.002239767,0.002653012],"category_scores_gemma":[0.02918112,0.0004216257,0.0007902556,0.001004801,0.001679708,0.004360535,0.00330629,0.004262473,0.002389329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009641741,"about_ca_system_score_gemma":0.001132655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001380282,"about_ca_topic_score_gemma":0.00148137,"domain_scores_codex":[0.9953011,0.00235804,0.000217392,0.0009274788,0.0008799883,0.0003159641],"domain_scores_gemma":[0.989183,0.006019929,0.0008934055,0.002202131,0.001311414,0.000390157],"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":[0.0007257875,0.0007183481,0.007942666,0.0002978945,0.0001920572,0.0002381036,0.0002591108,0.6012629,0.01537262,0.0542389,0.01458284,0.3041687],"study_design_scores_gemma":[0.0000304513,0.0001171335,0.0004660893,0.00001989479,0.00001289725,0.00005349622,0.00002524037,0.9671178,0.003231254,0.02801642,0.0008947017,0.00001462878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1303756,0.001752102,0.8517903,0.003446519,0.0002142988,0.00007087617,0.0002337597,0.005425395,0.006691123],"genre_scores_gemma":[0.8469238,0.0005975158,0.14331,0.0009387496,0.0002488592,0.0001089334,0.00087689,0.0007976426,0.006197473],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006829215,"threshold_uncertainty_score":0.03611678,"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."}}