A Hilbert space embedding of a distribution—in short, a kernel mean embedding—has
recently emerged as a powerful tool for machine learning and statistical inference. The basic …

This paper is an attempt to bridge the conceptual gaps between researchers working on the
two widely used approaches based on positive definite kernels: Bayesian learning or …

Recent advances in probabilistic modelling have led to a large number of simulation-based
inference algorithms which do not require numerical evaluation of likelihoods. However, a …

We propose a general purpose variational inference algorithm that forms a natural
counterpart of gradient descent for optimization. Our method iteratively transports a set of …

We derive a new discrepancy statistic for measuring differences between two probability
distributions based on combining Stein's identity and the reproducing kernel Hilbert space …

Statistical signal processing applications usually require the estimation of some parameters
of interest given a set of observed data. These estimates are typically obtained either by …

This paper studies the universal approximation property of deep neural networks for
representing probability distributions. Given a target distribution $\pi $ and a source …

Stein variational gradient descent (SVGD) is a deterministic sampling algorithm that
iteratively transports a set of particles to approximate given distributions, based on a …

Recent work has shown that deep generative models can assign higher likelihood to out-of-
distribution data sets than to their training data (Nalisnick et al., 2019; Choi et al., 2019). We …

Abstract Approximate Markov chain Monte Carlo (MCMC) offers the promise of more rapid
sampling at the cost of more biased inference. Since standard MCMC diagnostics fail to …