English

Generalization Properties and Implicit Regularization for Multiple Passes SGM

Machine Learning 2016-05-27 v1 Machine Learning

Abstract

We study the generalization properties of stochastic gradient methods for learning with convex loss functions and linearly parameterized functions. We show that, in the absence of penalizations or constraints, the stability and approximation properties of the algorithm can be controlled by tuning either the step-size or the number of passes over the data. In this view, these parameters can be seen to control a form of implicit regularization. Numerical results complement the theoretical findings.

Keywords

Cite

@article{arxiv.1605.08375,
  title  = {Generalization Properties and Implicit Regularization for Multiple Passes SGM},
  author = {Junhong Lin and Raffaello Camoriano and Lorenzo Rosasco},
  journal= {arXiv preprint arXiv:1605.08375},
  year   = {2016}
}

Comments

26 pages, 4 figures. To appear in ICML 2016

R2 v1 2026-06-22T14:10:30.732Z