140 citations · 735 across the 46 of their papers we have counts for
7 papers · 1 filter
Data-driven Sequential Monte Carlo in Probabilistic Programming
Yura N Perov, Tuan Anh Le, Frank Wood
Most of Markov Chain Monte Carlo (MCMC) and sequential Monte Carlo (SMC) algorithms in existing probabilistic programming systems suboptimally use only model priors as proposal dis…
A New Approach to Probabilistic Programming Inference
Frank Wood, Jan Willem van de Meent, Vikash Mansinghka
We introduce and demonstrate a new approach to inference in expressive probabilistic programming languages based on particle Markov chain Monte Carlo. Our approach is simple to imp…
Black-Box Policy Search with Probabilistic Programs
Jan-Willem van de Meent, Brooks Paige, David Tolpin +1
In this work, we explore how probabilistic programs can be used to represent policies in sequential decision problems. In this formulation, a probabilistic program is a black-box s…
Maximum a Posteriori Estimation by Search in Probabilistic Programs
David Tolpin, Frank Wood
We introduce an approximate search algorithm for fast maximum a posteriori probability estimation in probabilistic programs, which we call Bayesian ascent Monte Carlo (BaMC). Proba…
Particle Gibbs with Ancestor Sampling for Probabilistic Programs
Jan-Willem van de Meent, Hongseok Yang, Vikash Mansinghka +1
Particle Markov chain Monte Carlo techniques rank among current state-of-the-art methods for probabilistic program inference. A drawback of these techniques is that they rely on im…
Path Finding under Uncertainty through Probabilistic Inference
David Tolpin, Brooks Paige, Jan Willem van de Meent +1
We introduce a new approach to solving path-finding problems under uncertainty by representing them as probabilistic models and applying domain-independent inference algorithms to…
Output-Sensitive Adaptive Metropolis-Hastings for Probabilistic Programs
David Tolpin, Jan Willem van de Meent, Brooks Paige +1
We introduce an adaptive output-sensitive Metropolis-Hastings algorithm for probabilistic models expressed as programs, Adaptive Lightweight Metropolis-Hastings (AdLMH). The algori…