ABSTRACT Statisticians often use Monte Carlo methods to approximate probability
distributions, primarily with Markov chain Monte Carlo and importance sampling. Sequential …

Probabilistic programming promises to simplify and democratize probabilistic machine
learning, but successful probabilistic programming systems require flexible, generic and …

We introduce a method for using deep neural networks to amortize the cost of inference in
models from the family induced by universal probabilistic programming languages …

A core problem in statistics and probabilistic machine learning is to compute probability
distributions and expectations. This is the fundamental problem of Bayesian statistics and …

Actions description languages (ADLs), such as STRIPS, PDDL, and RDDL specify the input
format for planning algorithms. Unfortunately, their syntax is familiar to planning experts only …

Anglican is a probabilistic programming system designed to interoperate with Clojure and
other JVM languages. We introduce the programming language Anglican, outline our design …

We develop nested variational inference (NVI), a family of methods that learn proposals for
nested importance samplers by minimizing an forward or reverse KL divergence at each …

Imagine a world where computational simulations can be inverted as easily as running them
forwards, where data can be used to refine models automatically, and where the only …

We propose an interacting contour stochastic gradient Langevin dynamics (ICSGLD)
sampler, an embarrassingly parallel multiple-chain contour stochastic gradient Langevin …

Abstract We introduce Support Decomposition Variational Inference (SDVI), a new
variational inference (VI) approach for probabilistic programs with stochastic support …