English

Closed Form Variational Objectives For Bayesian Neural Networks with a Single Hidden Layer

Machine Learning 2018-12-04 v2 Machine Learning

Abstract

In this note we consider setups in which variational objectives for Bayesian neural networks can be computed in closed form. In particular we focus on single-layer networks in which the activation function is piecewise polynomial (e.g. ReLU). In this case we show that for a Normal likelihood and structured Normal variational distributions one can compute a variational lower bound in closed form. In addition we compute the predictive mean and variance in closed form. Finally, we also show how to compute approximate lower bounds for other likelihoods (e.g. softmax classification). In experiments we show how the resulting variational objectives can help improve training and provide fast test time predictions.

Keywords

Cite

@article{arxiv.1811.00686,
  title  = {Closed Form Variational Objectives For Bayesian Neural Networks with a Single Hidden Layer},
  author = {Martin Jankowiak},
  journal= {arXiv preprint arXiv:1811.00686},
  year   = {2018}
}

Comments

Bayesian Deep Learning Workshop @ NeurIPS 2018; 11 pages

R2 v1 2026-06-23T05:01:35.052Z