We advocate an optimization-centric view of Bayesian inference. Our inspiration is the
representation of Bayes' rule as infinite-dimensional optimization (Csisz´ r, 1975; Donsker …

We advocate an optimization-centric view on and introduce a novel generalization of
Bayesian inference. Our inspiration is the representation of Bayes' rule as infinite …

Contrastive representation learning seeks to acquire useful representations by estimating
the shared information between multiple views of data. Here, the choice of data …

Recent research has seen several advances relevant to black-box VI, but the current state of
automatic posterior inference is unclear. One such advance is the use of normalizing flows …

To make decisions based on a model fit with auto-encoding variational Bayes (AEVB),
practitioners often let the variational distribution serve as a surrogate for the posterior …

The estimation of an f-divergence between two probability distributions based on samples is
a fundamental problem in statistics and machine learning. Most works study this problem …

Bayesian calibration of black-box computer models offers an established framework for
quantification of uncertainty of model parameters and predictions. Traditional Bayesian …

Natural language often exhibits inherent hierarchical structure ingrained with complex
syntax and semantics. However, most state-of-the-art deep generative models learn …

Abstract Successful applications of InfoNCE (Information Noise-Contrastive Estimation) and
its variants have popularized the use of contrastive variational mutual information (MI) …

Bayesian decision theory outlines a rigorous framework for making optimal decisions based
on maximizing expected utility over a model posterior. However, practitioners often do not …