6 search results - page 1 / 2 » Algorithm portfolio selection as a bandit problem with unbou... |
AMAI
2011
Springer
12 years 5 months ago
2011
Springer
LION
2010
Springer
13 years 9 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...
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 2 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...
COLT
2005
Springer
13 years 7 months ago
2005
Springer
External regret compares the performance of an online algorithm, selecting among N actions, to the performance of the best of those actions in hindsight. Internal regret compares ...