Vprop: Variational Inference using RMSprop
Abstract
Many computationally-efficient methods for Bayesian deep learning rely on continuous optimization algorithms, but the implementation of these methods requires significant changes to existing code-bases. In this paper, we propose Vprop, a method for Gaussian variational inference that can be implemented with two minor changes to the off-the-shelf RMSprop optimizer. Vprop also reduces the memory requirements of Black-Box Variational Inference by half. We derive Vprop using the conjugate-computation variational inference method, and establish its connections to Newton's method, natural-gradient methods, and extended Kalman filters. Overall, this paper presents Vprop as a principled, computationally-efficient, and easy-to-implement method for Bayesian deep learning.
Cite
@article{arxiv.1712.01038,
title = {Vprop: Variational Inference using RMSprop},
author = {Mohammad Emtiyaz Khan and Zuozhu Liu and Voot Tangkaratt and Yarin Gal},
journal= {arXiv preprint arXiv:1712.01038},
year = {2017}
}