Streaming Variational Bayes

07/25/2013 ∙ by Tamara Broderick, et al. ∙ 0

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.



There are no comments yet.


page 1

page 2

page 3

page 4

Code Repositories


This is code associated with the paper: Broderick, T, Boyd, N, Wibisono, A, Wilson, AC, and Jordan, MI. Streaming variational Bayes. Neural Information Processing Systems, 2013.

view repo


This is the repository for the open source code in the amidst project.

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.