DOE OSTI · 1865129
A backward SDE method for uncertainty quantification in deep learning
Abstract
Here, we develop a backward stochastic differential equation based probabilistic machine learning method, which formulates a class of stochastic neural networks as a stochastic optimal control problem. An efficient stochastic gradient descent algorithm is introduced with the gradient computed through a backward stochastic differential equation. Convergence analysis for stochastic gradient descent optimization and numerical experiments for applications of stochastic neural networks are carried out to validate our methodology in both theory and performance.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Archibald, Richard, Bao, Feng, Cao, Yanzhao, Zhang, He. 2022-01-01. A backward SDE method for uncertainty quantification in deep learning. https://doi.org/10.3934/dcdss.2022062. https://searchnasa.com/record/osti%3A1865129/a-backward-sde-method-for-uncertainty-quantification-in-deep-learning
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.