Search Results for author: Kenyon Ng

Found 2 papers, 0 papers with code

Temperature Optimization for Bayesian Deep Learning

no code implementations8 Oct 2024 Kenyon Ng, Chris van der Heide, Liam Hodgkinson, Susan Wei

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 the posterior predictive distribution (PPD).

Deep Learning

Pathwise Gradient Variance Reduction with Control Variates in Variational Inference

no code implementations8 Oct 2024 Kenyon Ng, Susan Wei

In this work, we review existing control-variates-based variance reduction methods for pathwise gradient estimators to assess their effectiveness.

Variational Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.