263 search results - page 4 / 53 » Regret Bounds for Prediction Problems |
ALT
2010
Springer
13 years 7 months ago
2010
Springer
: In many prediction problems, including those that arise in computer security and computational finance, the process generating the data is best modeled as an adversary with whom ...
DISOPT
2010
13 years 5 months ago
2010
While the complexity of min-max and min-max regret versions of most classical combinatorial optimization problems has been thoroughly investigated, there are very few studies abou...
ORL
2008
13 years 5 months ago
2008
This paper focuses on tractable instances of interval data minmax regret graph problems. More precisely, we provide polynomial and pseudopolynomial algorithms for sets of particul...
JMLR
2010
13 years 16 days ago
2010
This work deals with four classical prediction settings, namely full information, bandit, label efficient and bandit label efficient as well as four different notions of regret: p...
COLT
2010
Springer
13 years 3 months ago
2010
Springer
Multiarmed bandit problem is a typical example of a dilemma between exploration and exploitation in reinforcement learning. This problem is expressed as a model of a gambler playi...