Download PDFOpen PDF in browser

Quasi-Monte Carlo Flows

EasyChair Preprint no. 684

6 pagesDate: December 17, 2018


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

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Florian Wenzel and Alexander Buchholz and Stephan Mandt},
  title = {Quasi-Monte Carlo Flows},
  howpublished = {EasyChair Preprint no. 684},
  doi = {10.29007/gxnq},
  year = {EasyChair, 2018}}
Download PDFOpen PDF in browser