A backward SDE method for uncertainty quantification in deep learning

DOI10.3934/dcdss.2022062zbMath1495.60064arXiv2011.14145OpenAlexW3150057971MaRDI QIDQ2676245

Yanzhao Cao, Feng Bao, He Zhang, Richard Archibald

Publication date: 27 September 2022

Published in: Discrete and Continuous Dynamical Systems. Series S (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.14145

zbMATH Keywords

stochastic optimal controlstochastic gradient descentstochastic neural networksprobabilistic machine learning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Optimal stochastic control (93E20) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35)

Related Items

Numerical Analysis for Convergence of a Sample-Wise Backpropagation Method for Training Stochastic Neural Networks

Uses Software

• SBEED

Cites Work

• Unnamed Item
• On some recent aspects of stochastic control and their applications
• Solving forward-backward stochastic differential equations explicitly -- a four step scheme
• A numerical scheme for BSDEs
• Representation theorems for backward stochastic differential equations
• A mean-field optimal control formulation of deep learning
• Recent Developments in Numerical Methods for Fully Nonlinear Second Order Partial Differential Equations
• A General Stochastic Maximum Principle for Optimal Control Problems
• Backward Stochastic Differential Equations in Finance
• An Efficient Gradient Projection Method for Stochastic Optimal Control Problems
• Iterative Importance Sampling Algorithms for Parameter Estimation
• Stable architectures for deep neural networks
• Non-convex Optimization for Machine Learning
• A New Kind of Accurate Numerical Method for Backward Stochastic Differential Equations
• Numerical Algorithms for Forward-Backward Stochastic Differential Equations