Streaming Variational Bayes
Machine Learning
2013-11-22 v2 Machine Learning
Abstract
We present SDA-Bayes, a framework for (S)treaming, (D)istributed, (A)synchronous computation of a Bayesian posterior. The framework makes streaming updates to the estimated posterior according to a user-specified approximation batch primitive. We demonstrate the usefulness of our framework, with variational Bayes (VB) as the primitive, by fitting the latent Dirichlet allocation model to two large-scale document collections. We demonstrate the advantages of our algorithm over stochastic variational inference (SVI) by comparing the two after a single pass through a known amount of data---a case where SVI may be applied---and in the streaming setting, where SVI does not apply.
Keywords
Cite
@article{arxiv.1307.6769,
title = {Streaming Variational Bayes},
author = {Tamara Broderick and Nicholas Boyd and Andre Wibisono and Ashia C. Wilson and Michael I. Jordan},
journal= {arXiv preprint arXiv:1307.6769},
year = {2013}
}
Comments
25 pages, 3 figures, 1 table