Barron Space Representations for Elliptic PDEs with Homogeneous Boundary Conditions
By: Ziang Chen, Liqiang Huang
Potential Business Impact:
Lets computers solve hard math problems faster.
We study the approximation complexity of high-dimensional second-order elliptic PDEs with homogeneous boundary conditions on the unit hypercube, within the framework of Barron spaces. Under the assumption that the coefficients belong to suitably defined Barron spaces, we prove that the solution can be efficiently approximated by two-layer neural networks, circumventing the curse of dimensionality. Our results demonstrate the expressive power of shallow networks in capturing high-dimensional PDE solutions under appropriate structural assumptions.
Similar Papers
Approximation Rates of Shallow Neural Networks: Barron Spaces, Activation Functions and Optimality Analysis
Machine Learning (CS)
Makes AI learn better with fewer steps.
Does the Barron space really defy the curse of dimensionality?
Functional Analysis
Makes AI learn better by understanding complex patterns.
What Can One Expect When Solving PDEs Using Shallow Neural Networks?
Numerical Analysis
Neural networks learn math problems better.