109 search results - page 1 / 22 » Algorithm Selection as a Bandit Problem with Unbounded Losse... |
LION
2010
Springer
13 years 8 months ago
2010
Springer
Abstract. Algorithm selection is typically based on models of algorithm performance learned during a separate offline training sequence, which can be prohibitively expensive. In r...
AMAI
2011
Springer
12 years 4 months ago
2011
Springer
ALT
2006
Springer
13 years 8 months ago
2006
Springer
In this paper the sequential prediction problem with expert advice is considered when the loss is unbounded under partial monitoring scenarios. We deal with a wide class of the par...
ALT
2008
Springer
14 years 1 months ago
2008
Springer
In this paper we consider the problem of actively learning the mean values of distributions associated with a finite number of options (arms). The algorithms can select which opti...
ICML
2006
IEEE
14 years 5 months ago
2006
IEEE
We formalize the associative bandit problem framework introduced by Kaelbling as a learning-theory problem. The learning environment is modeled as a k-armed bandit where arm payof...