swMATH ID: 22203
Software Authors: Mohammad Emtiyaz Khan, Zuozhu Liu, Voot Tangkaratt, Yarin Gal
Description: Vprop: Variational Inference using RMSprop. 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.
Homepage: https://arxiv.org/abs/1712.01038
Keywords: Machine Learning; arXiv stat.ML; Learning; arXiv cs.LG; arXiv; Bayesian deep learning; Gaussian variational inference; RMSprop optimizer
Related Software: Adam; RMSprop; AdaGrad; PRMLT
Cited in: 1 Publication

Cited in 1 Serial

1 Statistics and Computing

Citations by Year