← Search

Maciej Korzepa

2 accepted papers

2021

Improving predictions of Bayesian neural nets via local linearization

AISTATS 2021poster

The generalized Gauss-Newton (GGN) approximation is often used to make practical Bayesian deep learning approaches scalable by replacing a second order derivative with a product of first order derivatives. In this paper we argue that the GGN approximation should be understood as a local linearizatio…

2019

Approximate Inference Turns Deep Networks into Gaussian Processes

NeurIPS 2019poster

Deep neural networks (DNN) and Gaussian processes (GP) are two powerful models with several theoretical connections relating them, but the relationship between their training methods is not well understood. In this paper, we show that certain Gaussian posterior approximations for Bayesian DNNs are e…