{"id":"W3126985315","doi":"10.48550/arxiv.2107.04497","title":"Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Heteroscedasticity; Variance (accounting); Weighting; Computer science; Noise (video); Mean squared error; Regression; Artificial intelligence; Statistics; Algorithm; Mathematics; Machine learning; Pattern recognition (psychology)","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":[0.004059708,0.001363403,0.001782937,0.0005999905,0.000438993,0.001361516,0.003178425,0.002088913,0.001953433],"category_scores_gemma":[0.00725641,0.0005238875,0.000825236,0.001011005,0.001119165,0.002284947,0.002190709,0.002731288,0.001112684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001329559,"about_ca_system_score_gemma":0.00151555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003865827,"about_ca_topic_score_gemma":0.005569877,"domain_scores_codex":[0.9981562,0.0006542332,0.00006795034,0.0005385264,0.0004218455,0.0001612577],"domain_scores_gemma":[0.9973859,0.0009775802,0.0002723784,0.0007406017,0.0005027,0.0001208122],"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":[0.0005853979,0.0003445921,0.002485045,0.0001874068,0.0002289983,0.0001473682,0.0001373915,0.5738537,0.01687687,0.03318444,0.01333964,0.3586292],"study_design_scores_gemma":[0.00001206663,0.00003128154,0.0001895037,0.000007654963,0.000009407903,0.00002065709,0.000005495228,0.9862283,0.002713174,0.01006458,0.0007075605,0.00001017905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01625544,0.0003869315,0.9800785,0.0002516345,0.00006209755,0.00003031191,0.0001442204,0.00165725,0.001133734],"genre_scores_gemma":[0.5527093,0.000382734,0.4328127,0.0007484283,0.0002011151,0.0001824997,0.001769141,0.0007873398,0.01040681],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004059708,"threshold_uncertainty_score":0.02147001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0654492402742479,"score_gpt":0.2039036817270097,"score_spread":0.1384544414527618,"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."}}