A trust-region method for stochastic variational inference with applications to streaming data

Abstract

Stochastic variational inference allows for fast posterior inference in complex Bayesian models. However, the algorithm is prone to local optima which can make the quality of the posterior approximation sensitive to the choice of hyperparameters and initialization. We address this problem by replacing the natural gradient step of stochastic varitional inference with a trust-region update. We show that this leads to generally better results and reduced sensitivity to hyperparameters. We also describe a new strategy for variational inference on streaming data and show that here our trust-region method is crucial for getting good performance.

in Proceedings of the 32nd International Conference on Machine Learning, 2015

References in corpus (5)

• Streaming Variational Bayes
• Scalable Recommendation with Poisson Factorization
• On the saddle point problem for non-convex optimization
• Structured Stochastic Variational Inference
• Smoothed Gradients for Stochastic Variational Inference

Cited by in corpus (6)

• An introduction to variational inference in Geophysical inverse problems
• Advances in Variational Inference
• Trust-Region Variational Inference with Gaussian Mixture Models
• Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning
• Faster Stochastic Variational Inference using Proximal-Gradient Methods with General Divergence Functions
• The Population Posterior and Bayesian Inference on Streams