Improved strongly adaptive online learning using coin betting

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

Improved strongly adaptive online learning using coin betting

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

Research output: Contribution to conference › Paper › peer-review

Abstract

This paper describes a new parameter-free online learning algorithm for changing environments. In comparing against algorithms with the same time complexity as ours, we obtain a strongly adaptive regret bound that is a factor of at least √log(T) better, where T is the time horizon. Empirical results show that our algorithm outperforms state-of-the-art methods in learning with expert advice and metric learning scenarios.

Original language	English (US)
State	Published - 2017
Externally published	Yes
Event	20th International Conference on Artificial Intelligence and Statistics, AISTATS 2017 - Fort Lauderdale, United States Duration: Apr 20 2017 → Apr 22 2017

Conference

Conference	20th International Conference on Artificial Intelligence and Statistics, AISTATS 2017
Country/Territory	United States
City	Fort Lauderdale
Period	4/20/17 → 4/22/17

ASJC Scopus subject areas

Artificial Intelligence
Statistics and Probability

Cite this

@conference{1eb739118c35497b8b26e4f6d12e21cf,

title = "Improved strongly adaptive online learning using coin betting",

abstract = "This paper describes a new parameter-free online learning algorithm for changing environments. In comparing against algorithms with the same time complexity as ours, we obtain a strongly adaptive regret bound that is a factor of at least √log(T) better, where T is the time horizon. Empirical results show that our algorithm outperforms state-of-the-art methods in learning with expert advice and metric learning scenarios.",

author = "Jun, \{Kwang Sung\} and Francesco Orabona and Stephen Wright and Rebecca Willett",

year = "2017",

language = "English (US)",

}

TY - CONF

T1 - Improved strongly adaptive online learning using coin betting

AU - Jun, Kwang Sung

AU - Orabona, Francesco

AU - Wright, Stephen

AU - Willett, Rebecca

PY - 2017

Y1 - 2017

N2 - This paper describes a new parameter-free online learning algorithm for changing environments. In comparing against algorithms with the same time complexity as ours, we obtain a strongly adaptive regret bound that is a factor of at least √log(T) better, where T is the time horizon. Empirical results show that our algorithm outperforms state-of-the-art methods in learning with expert advice and metric learning scenarios.

AB - This paper describes a new parameter-free online learning algorithm for changing environments. In comparing against algorithms with the same time complexity as ours, we obtain a strongly adaptive regret bound that is a factor of at least √log(T) better, where T is the time horizon. Empirical results show that our algorithm outperforms state-of-the-art methods in learning with expert advice and metric learning scenarios.

UR - https://www.scopus.com/pages/publications/85083937416

UR - https://www.scopus.com/pages/publications/85083937416#tab=citedBy

M3 - Paper

AN - SCOPUS:85083937416

T2 - 20th International Conference on Artificial Intelligence and Statistics, AISTATS 2017

Y2 - 20 April 2017 through 22 April 2017

ER -

Improved strongly adaptive online learning using coin betting

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this