2025
ELBO, regularized maximum likelihood, and their common one-sample approximation for training stochastic neural networks
UAI 2025
Monte Carlo approximations are central to the training of stochastic neural networks in general, and Bayesian neural networks (BNNs) in particular. We observe that the common one-sample approximation of the standard training objective can be viewed both as maximizing the Evidence Lower Bound (ELBO)