conftrace_

2020 ICML ICML 2020

Efficiently Learning Adversarially Robust Halfspaces with Noise

Abstract

We study the problem of learning adversarially robust halfspaces in the distribution-independent setting. In the realizable setting, we provide necessary and sufficient conditions on the adversarial perturbation sets under which halfspaces are efficiently robustly learnable. In the presence of random label noise, we give a simple computationally efficient algorithm for this problem with respect to any $\ell_p$-perturbation.

🐣 Hot Topic Early Bird - surrogate loss

Authors

Omar Montasser, Surbhi Goel, Ilias Diakonikolas, Nathan Srebro

Topics

Machine Learning > Core Methods > Classification Machine Learning > Learning Types > Adversarial Learning Machine Learning > Optimization & Theory > Learning Theory

Keywords

adversarial robustness robust classification label noise halfspace learning surrogate loss

More from ICML 2020

All ICML 2020 papers →

Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules

Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching Approach

Transformation of ReLU-based recurrent neural networks from discrete-time to continuous-time

An end-to-end approach for the verification problem: learning the right distance

Confidence-Aware Learning for Deep Neural Networks

Topological Autoencoders