The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness
in ReLU Networks

The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks

2 March 2023

Gal Vardi

Peter L. Bartlett

Papers citing "The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks"

7 / 7 papers shown

Title
Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data Binghui Li Yuanzhi Li OOD 28 2 0 11 Oct 2024
Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization Spencer Frei Gal Vardi Peter L. Bartlett Nathan Srebro 27 22 0 02 Mar 2023
On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias Itay Safran Gal Vardi Jason D. Lee MLT 41 23 0 18 May 2022
On Margin Maximization in Linear and ReLU Networks Gal Vardi Ohad Shamir Nathan Srebro 40 27 0 06 Oct 2021
Towards Understanding Learning in Neural Networks with Linear Teachers Roei Sarussi Alon Brutzkus Amir Globerson FedML MLT 50 20 0 07 Jan 2021
Adversarial examples from computational constraints Sébastien Bubeck Eric Price Ilya P. Razenshteyn AAML 60 228 0 25 May 2018
Adversarial Machine Learning at Scale Alexey Kurakin Ian Goodfellow Samy Bengio AAML 256 3,102 0 04 Nov 2016