{"id":"W3116747493","doi":"","title":"All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference.","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Exponential family; Inference; Estimator; Computer science; Grid; Applied mathematics; Exponential function; Hyperparameter optimization; Upper and lower bounds; Mathematical optimization; Mathematics; Artificial intelligence; Statistics; Mathematical analysis","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":[0.0005175888,0.0002070386,0.0001878159,0.0001728459,0.00007479164,0.0004290553,0.001866935,0.00007556414,0.0002454061],"category_scores_gemma":[0.0002607211,0.0001626243,0.00005830438,0.0003967569,0.00004260758,0.000495318,0.0002483976,0.0008651259,0.000097581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006280489,"about_ca_system_score_gemma":0.0001552042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004269988,"about_ca_topic_score_gemma":0.0001553018,"domain_scores_codex":[0.9978173,0.0003240551,0.0004075604,0.0005148248,0.0006579698,0.0002782809],"domain_scores_gemma":[0.9992319,0.0002090028,0.0001746585,0.0002169293,0.00009842061,0.0000690697],"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":[0.00004556109,0.0001299457,0.02455979,0.00001256492,0.00001825631,0.00006643475,0.004650504,0.002805186,0.0009035618,0.9574481,0.00002488937,0.009335207],"study_design_scores_gemma":[0.0005724846,0.0001015181,0.1655728,0.00004841443,0.000002054508,0.000006143998,0.0001740331,0.8035541,0.00001430795,0.02908057,0.0006680709,0.0002055965],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2719261,0.00005601444,0.5707404,0.1024501,0.0005671904,0.0004378993,0.00002205481,0.0002268941,0.0535733],"genre_scores_gemma":[0.9943931,0.00003263059,0.001394872,0.003962707,0.00009449488,0.00002979019,0.00004389091,0.000008423764,0.00004005876],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9283676,"threshold_uncertainty_score":0.6631627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06415591807818004,"score_gpt":0.3211540639702533,"score_spread":0.2569981458920733,"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."}}