5 papers
Global Convergence of DGM and PINN Algorithms for Solving Nonlinear PDEs
Justin Sirignano, Konstantinos Spiliopoulos, Samuel Cohen
The Deep Galerkin Method (DGM) and Physics Informed Neural Networks (PINNs) have become widely-used methods for solving partial differential equations (PDEs) in the rapidly growing…
Weak Convergence Analysis of Online Neural Actor-Critic Algorithms
Samuel Chun-Hei Lam, Justin Sirignano, Ziheng Wang
We prove that a single-layer neural network trained with the online actor critic algorithm converges in distribution to a random ordinary differential equation (ODE) as the number…
Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit
Konstantin Riedl, Konstantinos Spiliopoulos, Justin Sirignano
A convergence analysis is developed for the regularized Newton method for training neural networks (NNs) in the overparameterized limit. As the number of hidden units tends to infi…
Neural Actor-Critic Methods for Hamilton-Jacobi-Bellman PDEs: Asymptotic Analysis and Numerical Studies
Samuel N. Cohen, Jackson Hebner, Deqing Jiang +1
We mathematically analyze and numerically study an actor-critic machine learning algorithm for solving high-dimensional Hamilton-Jacobi-Bellman (HJB) partial differential equations…
Deep Hilbert--Galerkin Methods for Infinite-Dimensional PDEs and Optimal Control
Samuel N. Cohen, Filippo de Feo, Jackson Hebner +1
We develop deep learning-based approximation methods for fully nonlinear second-order PDEs on separable Hilbert spaces, such as HJB equations for infinite-dimensional control, by p…