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

DOI10.1137/22m1523765OpenAlexW4392385407MaRDI QIDQ6190298

Richard Archibald, Yanzhao Cao, Hui Sun, Feng Bao

Publication date: 5 March 2024

Published in: SIAM Journal on Numerical Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/22m1523765

zbMATH Keywords

convergence analysisbackward stochastic differential equationsprobabilistic learningstochastic gradient descentstochastic neural networks

Mathematics Subject Classification ID

Probabilistic models, generic numerical methods in probability and statistics (65C20) Applications of stochastic analysis (to PDEs, etc.) (60H30)

Cites Work

• Unnamed Item
• Unnamed Item
• Continuous-time stochastic control and optimization with financial applications
• Forward-backward stochastic differential equations and their applications
• Feedforward neural nets as discretization schemes for ODEs and DAEs
• Uncertainty quantification using Bayesian neural networks in classification: application to biomedical image segmentation
• B-PINNs: Bayesian physics-informed neural networks for forward and inverse PDE problems with noisy data
• Bayesian inference of non-linear multiscale model parameters accelerated by a deep neural network
• Quantifying model form uncertainty in Reynolds-averaged turbulence models with Bayesian deep neural networks
• Modeling the dynamics of PDE systems with physics-constrained deep auto-regressive networks
• A proposal on machine learning via dynamical systems
• A backward SDE method for uncertainty quantification in deep learning
• Robust Stochastic Approximation Approach to Stochastic Programming
• Backward Stochastic Differential Equations in Finance
• Stable architectures for deep neural networks
• Optimization Methods for Large-Scale Machine Learning
• Backward Stochastic Differential Equations
• A New Kind of Accurate Numerical Method for Backward Stochastic Differential Equations
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming

This page was built for publication: Numerical Analysis for Convergence of a Sample-Wise Backpropagation Method for Training Stochastic Neural Networks