Sciweavers

88 search results - page 1 / 18
» Scale-Free Algorithms for Online Linear Optimization
Sort
View
CORR
2012
Springer
210views Education» more  CORR 2012»
12 years 9 days ago
Towards minimax policies for online linear optimization with bandit feedback
We address the online linear optimization problem with bandit feedback. Our contribution is twofold. First, we provide an algorithm (based on exponential weights) with a regret of...
Sébastien Bubeck, Nicolò Cesa-Bianch...
COLT
2008
Springer
13 years 6 months ago
Competing in the Dark: An Efficient Algorithm for Bandit Linear Optimization
We introduce an efficient algorithm for the problem of online linear optimization in the bandit setting which achieves the optimal O ( T) regret. The setting is a natural general...
Jacob Abernethy, Elad Hazan, Alexander Rakhlin
ICRA
2009
IEEE
137views Robotics» more  ICRA 2009»
13 years 11 months ago
An optimized Linear Model Predictive Control solver for online walking motion generation
— This article addresses the fast solution of a Quadratic Program underlying a Linear Model Predictive Control scheme that generates walking motions. We introduce an algorithm wh...
Dimitar Dimitrov, Pierre-Brice Wieber, Olivier Sta...
COLT
2008
Springer
13 years 6 months ago
High-Probability Regret Bounds for Bandit Online Linear Optimization
We present a modification of the algorithm of Dani et al. [8] for the online linear optimization problem in the bandit setting, which with high probability has regret at most O ( ...
Peter L. Bartlett, Varsha Dani, Thomas P. Hayes, S...
ICDAR
2011
IEEE
12 years 4 months ago
Objective Function Design for MCE-Based Combination of On-line and Off-line Character Recognizers for On-line Handwritten Japane
—This paper describes effective object function design for combining on-line and off-line character recognizers for on-line handwritten Japanese text recognition. We combine on-l...
Bilan Zhu, Jinfeng Gao, Masaki Nakagawa