Approximating Positive Homogeneous Functions with Scale Invariant Neural Networks

作     者：Bamberger, Stefan Heckel, Reinhard Krahmer, Felix 

作者机构：Department of Mathematics Technical University of Munich Holsten Systems GmbH Germany Department of Computer Engineering Technical University of Munich Munich Center for Machine Learning Germany Department of Mathematics Munich Data Science Institute Technical University of Munich Munich Center for Machine Learning Germany 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2023年

核心收录：

主　　题：Recovery 

摘      要：We investigate to what extent it is possible to solve linear inverse problems with ReLu networks. Due to the scaling invariance arising from the linearity, an optimal reconstruction function f for such a problem is positive homogeneous, i.e., satisfies f(λx) = λf(x) for all non-negative λ. In a ReLu network, this condition translates to considering networks without bias terms. We first consider recovery of sparse vectors from few linear measurements. We prove that ReLu- networks with only one hidden layer cannot even recover 1-sparse vectors, not even approximately, and regardless of the width of the network. However, with two hidden layers, approximate recovery with arbitrary precision and arbitrary sparsity level s is possible in a stable way. We then extend our results to a wider class of recovery problems including low-rank matrix recovery and phase retrieval. Furthermore, we also consider the approximation of general positive homogeneous functions with neural networks. Extending previous work, we establish new results explaining under which conditions such functions can be approximated with neural networks. Our results also shed some light on the seeming contradiction between previous works showing that neural networks for inverse problems typically have very large Lipschitz constants, but still perform very well also for adversarial noise. Namely, the error bounds in our expressivity results include a combination of a small constant term and a term that is linear in the noise level, indicating that robustness issues may occur only for very small noise *** Codes 41A30, 68T07 Copyright © 2023, The Authors. All rights reserved.