English

Online learning with exponential weights in metric spaces

Machine Learning 2021-03-29 v1 Machine Learning Metric Geometry Statistics Theory Statistics Theory

Abstract

This paper addresses the problem of online learning in metric spaces using exponential weights. We extend the analysis of the exponentially weighted average forecaster, traditionally studied in a Euclidean settings, to a more abstract framework. Our results rely on the notion of barycenters, a suitable version of Jensen's inequality and a synthetic notion of lower curvature bound in metric spaces known as the measure contraction property. We also adapt the online-to-batch conversion principle to apply our results to a statistical learning framework.

Keywords

Cite

@article{arxiv.2103.14389,
  title  = {Online learning with exponential weights in metric spaces},
  author = {Quentin Paris},
  journal= {arXiv preprint arXiv:2103.14389},
  year   = {2021}
}

Comments

33 pages, 1 figure

R2 v1 2026-06-24T00:35:01.237Z