Abstract | ||
---|---|---|
We consider an online learning scenario in which the learner can make predictions on the basis of a fixed set of experts. We derive upper and lower relative loss bounds for a class of universal learning algorithms involving a switching dynamics over the choice of the experts. On the basis of the performance bounds we provide the optimal a priori discretization for learning the parameter that governs the switching dynamics. We demonstrate the new algorithm in the context of wireless networks. |
Year | Venue | Keywords |
---|---|---|
2003 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 16 | wireless networks,hmm,wireless,wireless network,stationary sequence,ai |
Field | DocType | Volume |
Online learning,Wireless network,Discretization,Wireless,Active learning (machine learning),Computer science,A priori and a posteriori,Theoretical computer science,Artificial intelligence,Hidden Markov model,Machine learning | Conference | 16 |
ISSN | Citations | PageRank |
1049-5258 | 27 | 3.10 |
References | Authors | |
13 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Claire Monteleoni | 1 | 327 | 24.15 |
Jaakkola, Tommi | 2 | 6948 | 968.29 |