An optimal-order backpropagation algorithm for stochastic neural networks

DOI10.1007/S10915-026-03379-5MaRDI QIDQ7289295zbMATH OpenFDO

Authors Daili Sheng, Minghui Song, Xiang Peng, Xuanqi Dong

Publication date 2 July 2026

Published in Journal of Scientific Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S10915-026-03379-5

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Stochastic programming (90C15) Optimal stochastic control (93E20)

Cites work

• A backward SDE method for uncertainty quantification in deep learning
• A direct sampling method and its integration with deep learning for inverse scattering problems with phaseless data
• A direct sampling-based deep learning approach for inverse medium scattering problems
• A forward-backward stochastic algorithm for quasi-linear PDEs
• A General Stochastic Maximum Principle for Optimal Control Problems
• A Numerical Method and its Error Estimates for the Decoupled Forward-Backward Stochastic Differential Equations
• A proposal on machine learning via dynamical systems
• A Stochastic Gradient Descent Approach for Stochastic Optimal Control
• A stochastic maximum principle approach for reinforcement learning with parameterized environment
• An efficient gradient projection method for stochastic optimal control problems
• An efficient numerical algorithm for solving data driven feedback control problems
• Backward stochastic differential equations. From linear to fully nonlinear theory
• Batch sample-wise stochastic optimal control via stochastic maximum principle
• Deep neural networks algorithms for stochastic control problems on finite horizon: convergence analysis
• Maximum principle based algorithms for deep learning
• New kinds of high-order multistep schemes for coupled forward backward stochastic differential equations
• Numerical Analysis for Convergence of a Sample-Wise Backpropagation Method for Training Stochastic Neural Networks
• Numerical methods for forward-backward stochastic differential equations
• On an artificial neural network for inverse scattering problems
• On Numerical Approximations of Forward-Backward Stochastic Differential Equations
• Optimal stochastic control, stochastic target problems, and backward SDE.
• Probabilistic interpretation for systems of quasilinear parabolic partial differential equations
• Second-order schemes for solving decoupled forward backward stochastic differential equations
• Solving elliptic optimal control problems via neural networks and optimality system
• Stable architectures for deep neural networks
• The steepest descent method for forward-backward SDEs

This page was built for publication: An optimal-order backpropagation algorithm for stochastic neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7289295)