Many modern unsupervised or semi-supervised machine learning algorithms rely on
Bayesian probabilistic models. These models are usually intractable and thus require …

We propose a new regularization method based on virtual adversarial loss: a new measure
of local smoothness of the conditional label distribution given input. Virtual adversarial loss …

Current black-box variational inference (BBVI) methods require the user to make numerous
design choices–such as the selection of variational objective and approximating family–yet …

This monograph aims at providing an introduction to key concepts, algorithms, and
theoretical results in machine learning. The treatment concentrates on probabilistic models …

We provide theoretical and empirical evidence that using tighter evidence lower bounds
(ELBOs) can be detrimental to the process of learning an inference network by reducing the …

Recent work used importance sampling ideas for better variational bounds on likelihoods.
We clarify the applicability of these ideas to pure probabilistic inference, by showing the …

Black-box variational inference (BBVI) now sees widespread use in machine learning and
statistics as a fast yet flexible alternative to Markov chain Monte Carlo methods for …

Abstract Minimizing the inclusive Kullback-Leibler (KL) divergence with stochastic gradient
descent (SGD) is challenging since its gradient is defined as an integral over the posterior …

This paper introduces Wasserstein variational inference, a new form of approximate
Bayesian inference based on optimal transport theory. Wasserstein variational inference …

The importance-weighted autoencoder (IWAE) approach of Burda et al. defines a sequence
of increasingly tighter bounds on the marginal likelihood of latent variable models. Recently …