{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002958323,0.0003494829,0.0003426184,0.0002005868,0.0002622698,0.000361724,0.002003984,0.0003409452,0.00006151289],"category_scores_gemma":[0.0001803185,0.0003770596,0.0001804122,0.0006495173,0.0000787223,0.0005722821,0.002558642,0.0009727923,0.0001342571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001873406,"about_ca_system_score_gemma":0.0002197944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001454865,"about_ca_topic_score_gemma":0.00007992934,"domain_scores_codex":[0.9972834,0.0003662715,0.0002410623,0.001594321,0.0001501882,0.0003647773],"domain_scores_gemma":[0.996961,0.0001440318,0.0004055056,0.002103337,0.0001794852,0.0002066672],"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":[0.0001167294,0.0007702654,0.04170998,0.001018853,0.0003550997,0.002886006,0.002938475,0.5422899,0.002633748,0.3764954,0.003711942,0.02507355],"study_design_scores_gemma":[0.000331695,0.00002825529,0.004387175,0.0002668806,0.00004091404,0.00001022053,0.00008622564,0.9884301,0.0001394687,0.003794544,0.002019922,0.0004646349],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1072511,0.00009467851,0.8881266,0.0003460183,0.00101767,0.0001483428,0.00000562344,0.0003716564,0.002638351],"genre_scores_gemma":[0.9857709,0.0002097009,0.0117712,0.0001695093,0.0001058245,0.000001298895,0.0001341337,0.0000205001,0.001816949],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8785198,"threshold_uncertainty_score":0.9998682,"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."}}