Learning Structural Weight Uncertainty for Sequential Decision-Making

Abstract

Learning probability distributions on the weights of neural networks (NNs) has recently proven beneficial in many applications. Bayesian methods, such as Stein variational gradient descent (SVGD), offer an elegant framework to reason about NN model uncertainty. However, by assuming independent Gaussian priors for the individual NN weights (as often applied), SVGD does not impose prior knowledge that there is often structural information (dependence) among weights. We propose efficient posterior learning of structural weight uncertainty, within an SVGD framework, by employing matrix variate Gaussian priors on NN parameters. We further investigate the learned structural uncertainty in sequential decision-making problems, including contextual bandits and reinforcement learning. Experiments on several synthetic and real datasets indicate the superiority of our model, compared with state-of-the-art methods.

Accepted by AISTATS 2018

Cited by in corpus (4)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• PID-GAN: A GAN Framework based on a Physics-informed Discriminator for Uncertainty Quantification with Physics
• Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition
• Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence Theory