no code implementations • 8 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).
no code implementations • 8 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.