A Backward SDE Method for Uncertainty Quantification in Deep Learning

2020/11/28 by Archibald, Richard, Bao, Feng, Cao, Yanzhao +1
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)

paper · doi:10.48550/arxiv.2011.14145

Abstract

We develop a probabilistic machine learning method, which formulates a class of stochastic neural networks by a stochastic optimal control problem. An efficient stochastic gradient descent algorithm is introduced under the stochastic maximum principle framework. Numerical experiments for applications of stochastic neural networks are carried out to validate the effectiveness of our methodology.

Related

• Stochastic Operator Network: A Stochastic Maximum Principle Based Approach to Operator Learning
• SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates
• Efficient Training of Neural SDEs Using Stochastic Optimal Control
• A deep learning method for solving stochastic optimal control problems driven by fully-coupled FBSDEs
• Solving stochastic optimal control problem via stochastic maximum principle with deep learning method