Sciweavers

14895 search results - page 3 / 2979
» Evaluating The Regret System
Sort
View
CORR
2010
Springer
49views Education» more  CORR 2010»
13 years 7 months ago
Distributed Algorithms for Learning and Cognitive Medium Access with Logarithmic Regret
The problem of distributed learning and channel access is considered in a cognitive network with multiple secondary users. The availability statistics of the channels are initially...
Animashree Anandkumar, Nithin Michael, Ao Kevin Ta...
ECAI
2004
Springer
14 years 28 days ago
Expectation Reasoning Using Regret and Disappointment
A critical aspect of an agent system is the ability to deal with unexpected situations to determine an appropriate course of action in a changing environment. In this paper, we inv...
Bình Vu Trân, James Harland, Margaret...
COLT
2004
Springer
13 years 11 months ago
Regret Bounds for Hierarchical Classification with Linear-Threshold Functions
We study the problem of classifying data in a given taxonomy when classifications associated with multiple and/or partial paths are allowed. We introduce an incremental algorithm u...
Nicolò Cesa-Bianchi, Alex Conconi, Claudio ...
ICASSP
2011
IEEE
12 years 11 months ago
Logarithmic weak regret of non-Bayesian restless multi-armed bandit
Abstract—We consider the restless multi-armed bandit (RMAB) problem with unknown dynamics. At each time, a player chooses K out of N (N > K) arms to play. The state of each ar...
Haoyang Liu, Keqin Liu, Qing Zhao
PODC
2009
ACM
14 years 8 months ago
Load balancing without regret in the bulletin board model
We analyze the performance of protocols for load balancing in distributed systems based on no-regret algorithms from online learning theory. These protocols treat load balancing a...
Éva Tardos, Georgios Piliouras, Robert D. K...