Sciweavers

89 search results - page 4 / 18
» A New Logarithmic Normalization Method in Games Theory
Sort
View
JMLR
2010
103views more  JMLR 2010»
13 years 2 months ago
Regret Bounds and Minimax Policies under Partial Monitoring
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...
Jean-Yves Audibert, Sébastien Bubeck
INFORMATICALT
2002
150views more  INFORMATICALT 2002»
13 years 7 months ago
Search for Dynamic Equilibrium in Duel Problems by Global Optimization
Two examples of open-loop differential games are considered in the paper. Starting with simplified dynamic Duel, further it was developed to differential economic Duel modelling pr...
Raimundas Matulevicius
CODES
2003
IEEE
14 years 20 days ago
A low power scheduler using game theory
In this paper, we describe a new methodology based on game theory for minimizing the average power of a circuit during scheduling in behavioral synthesis. The problem of schedulin...
N. Ranganathan, Ashok K. Murugavel
ECCC
2006
218views more  ECCC 2006»
13 years 7 months ago
Efficient Algorithms for Online Game Playing and Universal Portfolio Management
We introduce a new algorithm and a new analysis technique that is applicable to a variety of online optimization scenarios, including regret minimization for Lipschitz regret func...
Amit Agarwal, Elad Hazan
CIKM
2009
Springer
14 years 1 months ago
A signal-to-noise approach to score normalization
Score normalization is indispensable in distributed retrieval and fusion or meta-search where merging of result-lists is required. Distributional approaches to score normalization...
Avi T. Arampatzis, Jaap Kamps