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 of the switching-rate parameter that governs the switching dynamics. We demonstrate the algorithm in the context of wireless networks.
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/30584 |
| Date | 17 November 2005 |
| Creators | Monteleoni, Claire, Jaakkola, Tommi |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Format | 8 p., 10189026 bytes, 760649 bytes, application/postscript, application/pdf |
| Relation | Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory |
Page generated in 0.0023 seconds