2013
NeurIPS
NeurIPS 2013
Streaming Variational Bayes
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 primitive function. 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), both in the single-pass setting SVI was designed for and in the streaming setting, to which SVI does not apply.
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Natural Language Processing
📈
Trend Setter
- Topic Modeling
🐣
Hot Topic Early Bird
- posterior approximation
Authors
Topics
Artificial Intelligence > Bayesian & Probabilistic > Bayesian Learning
Machine Learning > Learning Types > Unsupervised Learning
Machine Learning > Optimization & Theory > Bayesian Inference
Machine Learning > Optimization & Theory > Distributed Learning
Machine Learning > Learning Types > Online Learning
Machine Learning > Bayesian & Probabilistic > Variational Inference
Machine Learning > Core Methods > Topic Modeling
Artificial Intelligence > Bayesian & Probabilistic > Variational Inference
Natural Language Processing > Applications > Topic Modeling