Note on the bias and variance of variational inference
Abstract
In this note, we study the relationship between the variational gap and the variance of the (log) likelihood ratio. We show that the gap can be upper bounded by some form of dispersion measure of the likelihood ratio, which suggests the bias of variational inference can be reduced by making the distribution of the likelihood ratio more concentrated, such as via averaging and variance reduction.
 Publication:

arXiv eprints
 Pub Date:
 June 2019
 DOI:
 10.48550/arXiv.1906.03708
 arXiv:
 arXiv:1906.03708
 Bibcode:
 2019arXiv190603708H
 Keywords:

 Computer Science  Machine Learning;
 Statistics  Machine Learning
 EPrint:
 5 pages