Sparse Stochastic Inference for Latent Dirichlet allocation
Machine Learning
2012-07-03 v1 Machine Learning
Abstract
We present a hybrid algorithm for Bayesian topic models that combines the efficiency of sparse Gibbs sampling with the scalability of online stochastic inference. We used our algorithm to analyze a corpus of 1.2 million books (33 billion words) with thousands of topics. Our approach reduces the bias of variational inference and generalizes to many Bayesian hidden-variable models.
Keywords
Cite
@article{arxiv.1206.6425,
title = {Sparse Stochastic Inference for Latent Dirichlet allocation},
author = {David Mimno and Matt Hoffman and David Blei},
journal= {arXiv preprint arXiv:1206.6425},
year = {2012}
}
Comments
Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012)