Defensive universal learning with experts
This paper shows how universal learning can be achieved with expert advice. To this aim, we specify an experts algorithm with the following characteristics: (a) it uses only feedback from the actions actually chosen (bandit setup), (b) it can be applied with countably infinite expert classes, and (c) it copes with losses that may grow in time appropriately slowly. We prove loss bounds against an adaptive adversary. Prom this, we obtain a master algorithm for "reactive" experts problems, which...[Show more]
|Collections||ANU Research Publications|
|Source:||Algorithmic Learning Theory: Proceedings of the 16th International Conference on Algorithmic Learning Theory (ALT-05) - LNAI 3734|
|01_Poland_Defensive_universal_learning_2005.pdf||263.3 kB||Adobe PDF||Request a copy|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.