A Backward SDE Method for Uncertainty Quantification in Deep Learning
This work addresses the problem of uncertainty quantification in deep learning for researchers and practitioners, offering an incremental approach.
This paper proposes a probabilistic machine learning method that models stochastic neural networks using a stochastic optimal control problem. It introduces an efficient stochastic gradient descent algorithm based on the stochastic maximum principle, and its effectiveness is validated through numerical experiments.
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.