Spectrally-normalized margin bounds for neural networks

Peter L. Bartlett, Dylan J. Foster, Matus Telgarsky

Research output: Contribution to journalConference articlepeer-review


This paper presents a margin-based multiclass generalization bound for neural networks that 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 trained with SGD on the mnist and cif ar 10 datasets, with both original and random labels; the bound, the Lipschitz constants, and the excess risks are all in direct correlation, suggesting both that SGD selects predictors whose complexity scales with the difficulty of the learning task, and secondly that the presented bound is sensitive to this complexity.

Original languageEnglish (US)
Pages (from-to)6241-6250
Number of pages10
JournalAdvances in Neural Information Processing Systems
StatePublished - 2017
Event31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, United States
Duration: Dec 4 2017Dec 9 2017

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing


Dive into the research topics of 'Spectrally-normalized margin bounds for neural networks'. Together they form a unique fingerprint.

Cite this