2 papers
cs.LG2026
Shallower ReLU Network Representations via Exact Linear Algebra
Kilian RueÃ, Gennadiy Averkov, Florestan Brunck +7
We prove that the maximum of real numbers is exactly representable by a ReLU network with two hidden layers for every . The constructions are obtained by reducing the…
math.NA2025
Neural Network Acceleration of Iterative Methods for Nonlinear Schrödinger Eigenvalue Problems
Daniel Peterseim, Jan-F. Pietschmann, Jonas Püschel +1
We present a novel approach to accelerate iterative methods to solve nonlinear Schrödinger eigenvalue problems using neural networks. Nonlinear eigenvector problems are fundamenta…