English

Perceptron Mistake Bounds

Machine Learning 2013-07-24 v2

Abstract

We present a brief survey of existing mistake bounds and introduce novel bounds for the Perceptron or the kernel Perceptron algorithm. Our novel bounds generalize beyond standard margin-loss type bounds, allow for any convex and Lipschitz loss function, and admit a very simple proof.

Cite

@article{arxiv.1305.0208,
  title  = {Perceptron Mistake Bounds},
  author = {Mehryar Mohri and Afshin Rostamizadeh},
  journal= {arXiv preprint arXiv:1305.0208},
  year   = {2013}
}
R2 v1 2026-06-22T00:09:39.905Z