@inproceedings{0991fb47ceff4ee983f4b81653e7edd0,
title = "The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks",
abstract = "In this work, we study the implications of the implicit bias of gradient flow on generalization and adversarial robustness in ReLU networks. We focus on a setting where the data consists of clusters and the correlations between cluster means are small, and show that in two-layer ReLU networks gradient flow is biased towards solutions that generalize well, but are vulnerable to adversarial examples. Our results hold even in cases where the network is highly overparameterized. Despite the potential for harmful overfitting in such settings, we prove that the implicit bias of gradient flow prevents it. However, the implicit bias also leads to non-robust solutions (susceptible to small adversarial ℓ2-perturbations), even though robust networks that fit the data exist.",
author = "Spencer Frei and Gal Vardi and Bartlett, {Peter L.} and Nathan Srebro",
note = "Publisher Copyright: {\textcopyright} 2023 Neural information processing systems foundation. All rights reserved.; 37th Conference on Neural Information Processing Systems, NeurIPS 2023 ; Conference date: 10-12-2023 Through 16-12-2023",
year = "2023",
language = "الإنجليزيّة",
series = "Advances in Neural Information Processing Systems",
editor = "A. Oh and T. Neumann and A. Globerson and K. Saenko and M. Hardt and S. Levine",
booktitle = "Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023",
}