Score: 0

Distributionally robust approximation property of neural networks

Published: October 10, 2025 | arXiv ID: 2510.09177v1

By: Mihriban Ceylan, David J. Prömel

Potential Business Impact:

Makes AI learn better with more math.

Business Areas:
Machine Learning Artificial Intelligence, Data and Analytics, Software

The universal approximation property uniformly with respect to weakly compact families of measures is established for several classes of neural networks. To that end, we prove that these neural networks are dense in Orlicz spaces, thereby extending classical universal approximation theorems even beyond the traditional $L^p$-setting. The covered classes of neural networks include widely used architectures like feedforward neural networks with non-polynomial activation functions, deep narrow networks with ReLU activation functions and functional input neural networks.

Page Count
19 pages

Category
Statistics:
Machine Learning (Stat)