On the performance of Direct Loss Minimization for Bayesian Neural NetworksDownload PDF

Published: 06 Dec 2022, Last Modified: 05 May 2023ICBINB posterReaders: Everyone
Keywords: variational inferece, evidence lower bound, direct loss minimization
Abstract: Direct Loss Minimization (DLM) has been proposed as a pseudo-Bayesian method motivated as regularized loss minimization. Compared to variational inference, it replaces the loss term in the evidence lower bound (ELBO) with the predictive log loss, which is the same loss function used in evaluation. A number of theoretical and empirical results in prior work suggest that DLM can significantly improve over ELBO optimization for some models. However, as we point out in this paper, this is not the case for Bayesian neural networks (BNNs). The paper explores the practical performance of DLM for BNN, the reasons for its failure and its relationship to optimizing the ELBO, uncovering some interesting facts about both algorithms.
0 Replies