{"id":"W3176268138","doi":"10.71781/10674","title":"On improving variational inference with low-variance multi-sample estimators","year":2020,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Université de Montréal","keywords":"Estimator; Inference; Variance (accounting); Sample (material); Statistics; Mathematics; Computer science; Econometrics; Artificial intelligence; Applied mathematics; Algorithm; Economics; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001448676,0.0004002651,0.0003896827,0.0001033355,0.0002381376,0.00163119,0.002628965,0.0001998223,0.0004987092],"category_scores_gemma":[0.0003901416,0.0003408472,0.00004965722,0.000526291,0.00002646898,0.0009404427,0.0002575821,0.0004538458,0.0004622166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006046674,"about_ca_system_score_gemma":0.001559255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001394594,"about_ca_topic_score_gemma":0.0002487,"domain_scores_codex":[0.9976738,0.00003889624,0.0003723964,0.00109655,0.0004775901,0.0003407657],"domain_scores_gemma":[0.9982407,0.0002740436,0.0004897687,0.0005968928,0.0002115796,0.0001870031],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004180111,0.0007141102,0.000784129,0.0006349894,0.0002080424,0.0002599435,0.008522394,0.001533264,0.0006393375,0.1771843,0.0002870038,0.8088145],"study_design_scores_gemma":[0.004127676,0.001734995,0.0240852,0.003719704,0.000171923,0.00003323835,0.000419159,0.9243644,0.01132066,0.01982899,0.005972482,0.004221622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002386127,0.00002046888,0.9884803,0.0002560964,0.0003919318,0.0005590109,0.00005667202,0.00001641499,0.00783294],"genre_scores_gemma":[0.2560503,0.000004023194,0.7416308,0.0001596645,0.00005619632,0.00008120138,0.0004040802,0.00003221178,0.001581451],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9228311,"threshold_uncertainty_score":0.9999043,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02337361973942188,"score_gpt":0.2991732527399016,"score_spread":0.2757996330004797,"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."}}