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. 1706.08498
239
1225
v1v2 (latest)

Spectrally-normalized margin bounds for neural networks

26 June 2017
Peter L. Bartlett
Dylan J. Foster
Matus Telgarsky
    ODL
ArXiv (abs)PDFHTML
Abstract

This paper presents a margin-based multiclass generalization bound for neural networks which scales with their margin-normalized "spectral complexity": their Lipschitz constant, meaning the product of the spectral norms of the weight matrices, times a certain correction factor. This bound is empirically investigated for a standard AlexNet network on the mnist and cifar10 datasets, with both original and random labels, where it tightly correlates with the observed excess risks.

View on arXiv
Comments on this paper