On-line Learning and Stochastic Approximations

Léon BottouCambridge 1999 · DOI · OpenAlex

Abstract

The convergence of online learning algorithms is analyzed using the tools of the stochastic approximation theory, and proved under very weak conditions. A general framework for online learning algorithms is first presented. This framework encompasses the most common online learning algorithms in use today, as illustrated by several examples. The stochastic approximation theory then provides general results describing the convergence of all these learning algorithms at once.
BibTeX
@inproceedings{bottou1999line,
  author = {Léon Bottou},
  title = {{On-line Learning and Stochastic Approximations}},
  booktitle = {Cambridge},
  year = {1999},
  doi = {10.1017/cbo9780511569920.003},
}

Loading related content...

Figure