Batch Stationary Distribution Estimation
Wen, Junfeng, Dai, Bo, Li, Lihong, Schuurmans, Dale
–arXiv.org Artificial Intelligence
We consider the problem of approximating the stationary distribution of an ergodic Markov chain given a set of sampled transitions. Classical simulation-based approaches assume access to the underlying process so that trajectories of sufficient length can be gathered to approximate stationary sampling. Instead, we consider an alternative setting where a fixed set of transitions has been collected beforehand, by a separate, possibly unknown procedure. The goal is still to estimate properties of the stationary distribution, but without additional access to the underlying system. We propose a consistent estimator that is based on recovering a correction ratio function over the given data. In particular, we develop a variational power method (VPM) that provides provably consistent estimates under general conditions. In addition to unifying a number of existing approaches from different subfields, we also find that VPM yields significantly better estimates across a range of problems, including queueing, stochastic differential equations, post-processing MCMC, and off-policy evaluation.
arXiv.org Artificial Intelligence
Mar-2-2020
- Country:
- North America
- Canada > Alberta (0.14)
- United States > Massachusetts
- Middlesex County > Cambridge (0.04)
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- Asia > Middle East
- Jordan (0.04)
- Israel > Jerusalem District
- Jerusalem (0.04)
- North America
- Genre:
- Research Report (0.40)
- Industry:
- Transportation (0.47)