Shifting Regret, Mirror Descent, and Matrices
File(s)
Published version
Accepted version
Author(s)
Gyorgy, A
Szepesvari, C
Type
Conference Paper
Abstract
We consider the problem of online prediction in
changing environments. In this framework the
performance of a predictor is evaluated as the
loss relative to an arbitrarily changing predictor,
whose individual components come from a base
class of predictors. Typical results in the literature
consider different base classes (experts, linear
predictors on the simplex, etc.) separately.
Introducing an arbitrary mapping inside the mirror
decent algorithm, we provide a framework
that unifies and extends existing results. As an
example, we prove new shifting regret bounds for
matrix prediction problems.
changing environments. In this framework the
performance of a predictor is evaluated as the
loss relative to an arbitrarily changing predictor,
whose individual components come from a base
class of predictors. Typical results in the literature
consider different base classes (experts, linear
predictors on the simplex, etc.) separately.
Introducing an arbitrary mapping inside the mirror
decent algorithm, we provide a framework
that unifies and extends existing results. As an
example, we prove new shifting regret bounds for
matrix prediction problems.
Date Issued
2016-06-30
Date Acceptance
2016-04-24
Citation
Journal of Machine Learning Research, 2016, 48, pp.2943-2951
ISSN
1532-4435
Publisher
Journal of Machine Learning Research
Start Page
2943
End Page
2951
Journal / Book Title
Journal of Machine Learning Research
Volume
48
Copyright Statement
© The Author(s) 2016.
Source
International Conference on Machine Learning
Subjects
Artificial Intelligence & Image Processing
08 Information And Computing Sciences
17 Psychology And Cognitive Sciences
Publication Status
Published
Start Date
2016-06-19
Finish Date
2016-06-24
Coverage Spatial
New York, NY, USA