Sciweavers

77 search results - page 8 / 16
» Efficient bandit algorithms for online multiclass prediction
Sort
View
ICML
2007
IEEE
14 years 7 months ago
Exponentiated gradient algorithms for log-linear structured prediction
Conditional log-linear models are a commonly used method for structured prediction. Efficient learning of parameters in these models is therefore an important problem. This paper ...
Amir Globerson, Terry Koo, Xavier Carreras, Michae...
COLT
2006
Springer
13 years 10 months ago
Logarithmic Regret Algorithms for Online Convex Optimization
In an online convex optimization problem a decision-maker makes a sequence of decisions, i.e., chooses a sequence of points in Euclidean space, from a fixed feasible set. After ea...
Elad Hazan, Adam Kalai, Satyen Kale, Amit Agarwal
TSP
2010
13 years 1 months ago
Energy efficient state estimation with wireless sensors through the use of predictive power control and coding
We study state estimation via wireless sensors over fading channels. Packet loss probabilities depend upon time-varying channel gains, packet lengths and transmission power levels ...
Daniel E. Quevedo, Anders Ahlén, Jan &Oslas...
COLT
2006
Springer
13 years 10 months ago
A Randomized Online Learning Algorithm for Better Variance Control
We propose a sequential randomized algorithm, which at each step concentrates on functions having both low risk and low variance with respect to the previous step prediction functi...
Jean-Yves Audibert
SODA
1994
ACM
88views Algorithms» more  SODA 1994»
13 years 8 months ago
Optimal Prediction for Prefetching in the Worst Case
Response time delays caused by I/O are a major problem in many systems and database applications. Prefetching and cache replacement methods are attracting renewed attention because...
P. Krishnan, Jeffrey Scott Vitter