2 papers
stat.ML2024
Pathwise Gradient Variance Reduction with Control Variates in Variational Inference
Kenyon Ng, Susan Wei
Variational inference in Bayesian deep learning often involves computing the gradient of an expectation that lacks a closed-form solution. In these cases, pathwise and score-functi…
stat.ML2024
Temperature Optimization for Bayesian Deep Learning
Kenyon Ng, Chris van der Heide, Liam Hodgkinson +1
The Cold Posterior Effect (CPE) is a phenomenon in Bayesian Deep Learning (BDL), where tempering the posterior to a cold temperature often improves the predictive performance of th…