Sciweavers

7 search results - page 1 / 2
» Minimizing Regret with Label Efficient Prediction
Sort
View
COLT
2004
Springer
13 years 9 months ago
Minimizing Regret with Label Efficient Prediction
We investigate label efficient prediction, a variant, proposed by Helmbold and Panizza, of the problem of prediction with expert advice. In this variant, the forecaster, after gues...
Nicolò Cesa-Bianchi, Gábor Lugosi, G...
COLT
2010
Springer
13 years 3 months ago
Regret Minimization With Concept Drift
In standard online learning, the goal of the learner is to maintain an average loss that is "not too big" compared to the loss of the best-performing function in a fixed...
Koby Crammer, Yishay Mansour, Eyal Even-Dar, Jenni...
ALT
2010
Springer
13 years 7 months ago
Optimal Online Prediction in Adversarial Environments
: 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 ...
Peter L. Bartlett
JMLR
2010
103views more  JMLR 2010»
13 years 10 days 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
COMCOM
2006
105views more  COMCOM 2006»
13 years 5 months ago
Dynamic bandwidth reservation for label switched paths: An on-line predictive approach
Managing the bandwidth allocated to a Label Switched Path in MPLS networks plays a major role for provisioning of Quality of Service and efficient use of resources. In doing so, t...
Tricha Anjali, Carlo Bruni, Daniela Iacoviello, Ca...