Data-driven Sequential Monte Carlo in Probabilistic Programming
Abstract
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 distributions. In this work, we describe an approach for training a discriminative model, namely a neural network, in order to approximate the optimal proposal by using posterior estimates from previous runs of inference. We show an example that incorporates a data-driven proposal for use in a non-parametric model in the Anglican probabilistic programming system. Our results show that data-driven proposals can significantly improve inference performance so that considerably fewer particles are necessary to perform a good posterior estimation.
Cite
@article{arxiv.1512.04387,
title = {Data-driven Sequential Monte Carlo in Probabilistic Programming},
author = {Yura N Perov and Tuan Anh Le and Frank Wood},
journal= {arXiv preprint arXiv:1512.04387},
year = {2016}
}
Comments
Black Box Learning and Inference, NIPS 2015 Workshop