We present high quality image synthesis results using diffusion probabilistic models, a class
of latent variable models inspired by considerations from nonequilibrium thermodynamics …

Abstract Annealed Importance Sampling (AIS) and its Sequential Monte Carlo (SMC)
extensions are state-of-the-art methods for estimating normalizing constants of probability …

In the context of lossy compression, Blau\& Michaeli (2019) adopt a mathematical notion of
perceptual quality and define the information rate-distortion-perception function …

Annealed importance sampling (AIS) and related algorithms are highly effective tools for
marginal likelihood estimation, but are not fully differentiable due to the use of Metropolis …

Variational autoencoders (VAEs) are powerful tools for learning latent representations of
data used in a wide range of applications. In practice, VAEs usually require multiple training …

Rate-distortion (RD) function, a key quantity in information theory, characterizes the
fundamental limit of how much a data source can be compressed subject to a fidelity …

A fundamental question in designing lossy data compression schemes is how well one can
do in comparison with the rate-distortion function, which describes the known theoretical …

Mutual information (MI) is a fundamental quantity in information theory and machine
learning. However, direct estimation of MI is intractable, even if the true joint probability …

The recently proposed Thermodynamic Variational Objective (TVO) leverages
thermodynamic integration to provide a family of variational inference objectives, which both …

Devising deep latent variable models for multi-modal data has been a long-standing theme
in machine learning research. Multi-modal Variational Autoencoders (VAEs) have been a …