Neural Networks With Dense Computational Graphs Are Not Universal Approximators
Organizations: Princeton University, Dept of CS · MIT, Dept of EECS and CSAIL · TUM, School of CIT, MCML, MDSI · Technion – IIT, Faculty of Mathematics
Abstract
We investigate the approximation capabilities of dense neural networks. While universal approximation theorems establish that sufficiently large architectures can approximate arbitrary continuous functions when there are no restrictions on the weights, we show that dense neural networks do not possess this universality. Our argument is based on a model compression approach, combining the weak regularity lemma with an interpretation of feedforward networks as message passing graph neural networks. We consider ReLU neural networks subject to natural constraints on weights and input and output dimensions, which model a notion of dense connectivity. Within this setting, we demonstrate the existence of Lipschitz continuous functions that cannot be approximated by such networks. This highlights intrinsic limitations of neural networks with dense layers and motivates the use of sparse connectivity as a necessary ingredient for achieving true universality.
Figures & tables
Neural Network Approximation Theory
Neural network approximation theory studies how network size, depth, activations, and structure determine the accuracy of functions and operators.
See all 261 papers