97 search results - page 6 / 20 » Logarithmic Regret Algorithms for Online Convex Optimization |
CORR
2010
Springer
13 years 5 months ago
2010
Springer
Online prediction methods are typically presented as serial algorithms running on a single processor. However, in the age of web-scale prediction problems, it is increasingly comm...
AAAI
2004
13 years 9 months ago
2004
This paper considers online stochastic optimization problems where time constraints severely limit the number of offline optimizations which can be performed at decision time and/...
COLT
2010
Springer
13 years 5 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...
COLT
2008
Springer
13 years 9 months ago
2008
Springer
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 ( ...
ICML
2009
IEEE
14 years 8 months ago
2009
IEEE
Many learning algorithms rely on the curvature (in particular, strong convexity) of regularized objective functions to provide good theoretical performance guarantees. In practice...