ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1810.02180
19
17

Improved Generalization Bounds for Adversarially Robust Learning

4 October 2018
Idan Attias
A. Kontorovich
Yishay Mansour
ArXivPDFHTML
Abstract

We consider a model of robust learning in an adversarial environment. The learner gets uncorrupted training data with access to possible corruptions that may be affected by the adversary during testing. The learner's goal is to build a robust classifier, which will be tested on future adversarial examples. The adversary is limited to kkk possible corruptions for each input. We model the learner-adversary interaction as a zero-sum game. This model is closely related to the adversarial examples model of Schmidt et al. (2018); Madry et al. (2017). Our main results consist of generalization bounds for the binary and multiclass classification, as well as the real-valued case (regression). For the binary classification setting, we both tighten the generalization bound of Feige et al. (2015), and are also able to handle infinite hypothesis classes. The sample complexity is improved from O(1ϵ4log⁡(∣H∣δ))O(\frac{1}{\epsilon^4}\log(\frac{|H|}{\delta}))O(ϵ41​log(δ∣H∣​)) to O(1ϵ2(kVC(H)log⁡32+α(kVC(H))+log⁡(1δ))O\big(\frac{1}{\epsilon^2}(kVC(H)\log^{\frac{3}{2}+\alpha}(kVC(H))+\log(\frac{1}{\delta})\big)O(ϵ21​(kVC(H)log23​+α(kVC(H))+log(δ1​)) for any α>0\alpha > 0α>0. Additionally, we extend the algorithm and generalization bound from the binary to the multiclass and real-valued cases. Along the way, we obtain results on fat-shattering dimension and Rademacher complexity of kkk-fold maxima over function classes; these may be of independent interest. For binary classification, the algorithm of Feige et al. (2015) uses a regret minimization algorithm and an ERM oracle as a black box; we adapt it for the multiclass and regression settings. The algorithm provides us with near-optimal policies for the players on a given training sample.

View on arXiv
Comments on this paper