Note on the bias and variance of variational inference
Machine Learning
2019-06-11 v1 Machine Learning
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.
Cite
@article{arxiv.1906.03708,
title = {Note on the bias and variance of variational inference},
author = {Chin-Wei Huang and Aaron Courville},
journal= {arXiv preprint arXiv:1906.03708},
year = {2019}
}
Comments
5 pages