English

Parameter-free online learning via model selection

Machine Learning 2018-01-08 v2 Machine Learning

Abstract

We introduce an efficient algorithmic framework for model selection in online learning, also known as parameter-free online learning. Departing from previous work, which has focused on highly structured function classes such as nested balls in Hilbert space, we propose a generic meta-algorithm framework that achieves online model selection oracle inequalities under minimal structural assumptions. We give the first computationally efficient parameter-free algorithms that work in arbitrary Banach spaces under mild smoothness assumptions; previous results applied only to Hilbert spaces. We further derive new oracle inequalities for matrix classes, non-nested convex sets, and Rd\mathbb{R}^{d} with generic regularizers. Finally, we generalize these results by providing oracle inequalities for arbitrary non-linear classes in the online supervised learning model. These results are all derived through a unified meta-algorithm scheme using a novel "multi-scale" algorithm for prediction with expert advice based on random playout, which may be of independent interest.

Keywords

Cite

@article{arxiv.1801.00101,
  title  = {Parameter-free online learning via model selection},
  author = {Dylan J. Foster and Satyen Kale and Mehryar Mohri and Karthik Sridharan},
  journal= {arXiv preprint arXiv:1801.00101},
  year   = {2018}
}

Comments

NIPS 2017

R2 v1 2026-06-22T23:32:47.275Z