Parameter-free online learning via model selection

Dylan J. Foster, Satyen Kale, Mehryar Mohri, Karthik Sridharan

Research output: Contribution to journalConference article

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 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.

Original languageEnglish (US)
Pages (from-to)6021-6031
Number of pages11
JournalAdvances in Neural Information Processing Systems
Volume2017-December
StatePublished - Jan 1 2017
Event31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, United States
Duration: Dec 4 2017Dec 9 2017

    Fingerprint

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Foster, D. J., Kale, S., Mohri, M., & Sridharan, K. (2017). Parameter-free online learning via model selection. Advances in Neural Information Processing Systems, 2017-December, 6021-6031.