Quasi-Monte Carlo Flows

EasyChair Preprint 684

Abstract

Normalizing flows provide a general approach to construct flexible variational posteriors. The parameters are learned by stochastic optimization of the variational bound, but inference can be slow due to high variance of the gradient estimator. We propose Quasi-Monte Carlo (QMC) flows which reduce the variance of the gradient estimator by one order of magnitude. First results show that QMC flows lead to faster inference and samples from the variational posterior cover the target space more evenly.

Keyphrases: Monte Carlo, Quasi-Monte Carlo, machine learning, statistics, variational inference

@booklet{EasyChair:684,
  author    = {Florian Wenzel and Alexander Buchholz and Stephan Mandt},
  title     = {Quasi-Monte Carlo Flows},
  doi       = {10.29007/gxnq},
  howpublished = {EasyChair Preprint 684},
  year      = {EasyChair, 2018}}