Two-layers neural networks for Schrödinger eigenvalue problems
Abstract
The aim of this article is to analyze numerical schemes using two-layer neural networks with infinite width for the resolution of high-dimensional Schrödinger eigenvalue problems with smooth interaction potentials and Neumann boundary condition on the unit cube in any dimension. More
precisely, any eigenfunction associated to the lowest eigenvalue of the Schrödinger operator is a unit L 2 norm minimizer of the associated energy. Using Barron’s representation of the solution with a probability measure defined on the set of parameter values and following the approach initially
suggested by Bach and Chizat [1], the energy is minimized thanks to a constrained gradient curve dynamic on the 2-Wasserstein space of the set of parameter values defining the neural network. We prove the existence of solutions to this constrained gradient curve. Furthermore, we prove that,
if it converges, the represented function is then an eigenfunction of the considered Schrödinger operator. At least up to our knowledge, this is the first work where this type of analysis is carried out to deal with the minimization of non-convex functionals.
Origin | Files produced by the author(s) |
---|