{"id":"W2952300048","doi":"10.48550/arxiv.1603.04733","title":"Structured and Efficient Variational Deep Learning with Matrix Gaussian\\n Posteriors","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"","keywords":"Gaussian; Matrix (chemical analysis); Applied mathematics; Computer science; Artificial intelligence; Gaussian process; Statistical physics; Mathematics; Mathematical optimization; Machine learning; Physics; Materials science; Quantum mechanics","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":[0.0001230389,0.0003261452,0.0002792827,0.0002192482,0.0002421914,0.0002872029,0.0009733002,0.000219805,0.00004300033],"category_scores_gemma":[0.00001885439,0.0002636897,0.0000670222,0.0003455912,0.0001302472,0.0002515528,0.001249989,0.0004501029,0.00002347295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000105484,"about_ca_system_score_gemma":0.0002351102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001699133,"about_ca_topic_score_gemma":0.00001197488,"domain_scores_codex":[0.9981973,0.00008694015,0.0001693701,0.001055609,0.0001394958,0.0003512599],"domain_scores_gemma":[0.9987069,0.00007280172,0.0003052421,0.0005669714,0.0001569963,0.0001911145],"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":[0.00009006781,0.00005021771,0.009834826,0.0002225851,0.0001336094,0.000393513,0.0007524293,0.1310205,0.00009982584,0.8543196,0.00001343638,0.003069459],"study_design_scores_gemma":[0.001216525,0.0002146794,0.03269886,0.0003842824,0.00009687699,0.00009627528,0.00009484232,0.8611723,0.0001025671,0.1026527,0.0002287728,0.00104136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1187788,0.00006437387,0.8792505,0.0002104284,0.0001876576,0.0001688461,0.000009033085,0.0001522879,0.001178013],"genre_scores_gemma":[0.9910281,0.00004541099,0.008183184,0.00003360832,0.00005249106,8.271346e-7,0.000006563781,0.00001637785,0.0006334764],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8722492,"threshold_uncertainty_score":0.9999815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01689345107360285,"score_gpt":0.1713345360625139,"score_spread":0.154441084988911,"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."}}