Online learning for changing environments using coin betting

Kwang Sung Jun, Francesco Orabona, Stephen Wright, Rebecca Willett

Research output: Contribution to journalArticlepeer-review

13 Scopus citations

Abstract

A key challenge in online learning is that classical algorithms can be slow to adapt to changing environments. Recent studies have proposed “meta” algorithms that convert any online learning algorithm to one that is adaptive to changing environments, where the adaptivity is analyzed in a quantity called the strongly-adaptive regret. This paper describes a new meta algorithm that has a strongly-adaptive regret bound that is a factor of √log(T) better than other algorithms with the same time complexity, where TT is the time horizon. We also extend our algorithm to achieve a first-order (i. e., dependent on the observed losses) strongly-adaptive regret bound for the first time, to our knowledge. At its heart is a new parameter-free algorithm for the learning with expert advice (LEA) problem in which experts sometimes do not output advice for consecutive time steps (i. e., sleeping experts). This algorithm is derived by a reduction from optimal algorithms for the so-called coin betting problem. Empirical results show that our algorithm outperforms state-of-the-art methods in both learning with expert advice and metric learning scenarios.
Original languageEnglish (US)
Pages (from-to)5282-5310
Number of pages29
JournalElectronic Journal of Statistics
Volume11
Issue number2
DOIs
StatePublished - Jan 1 2017
Externally publishedYes

ASJC Scopus subject areas

  • Statistics and Probability

Fingerprint

Dive into the research topics of 'Online learning for changing environments using coin betting'. Together they form a unique fingerprint.

Cite this