Stochastic Control for Bayesian Neural Network Training

In this paper, we propose to leverage the Bayesian uncertainty information encoded in parameter distributions to inform the learning procedure for Bayesian models. We derive a first principle stochastic differential equation for the training dynamics of the mean and uncertainty parameter in the variational distributions. On the basis of the derived Bayesian stochastic differential equation, we apply the methodology of stochastic optimal control on the variational parameters to obtain individually controlled learning rates. We show that the resulting optimizer, StochControlSGD, is significantly more robust to large learning rates and can adaptively and individually control the learning rates of the variational parameters. The evolution of the control suggests separate and distinct dynamical behaviours in the training regimes for the mean and uncertainty parameters in Bayesian neural networks.

Automated summary

This paper proposes a method to leverage the Bayesian uncertainty information encoded in parameter distributions to inform the learning procedure for Bayesian models. By deriving a Bayesian stochastic differential equation and applying stochastic optimal control, individually controlled learning rates are obtained for variational parameters. The resulting optimizer shows robustness to large learning rates and can adaptively and individually control the learning rates.