Skip navigation
Skip navigation

Defensive universal learning with experts

Poland, Jan; Hutter, Marcus


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]

CollectionsANU Research Publications
Date published: 2005
Type: Conference paper
Source: Algorithmic Learning Theory: Proceedings of the 16th International Conference on Algorithmic Learning Theory (ALT-05) - LNAI 3734
DOI: 10.1007/11564089_28


File Description SizeFormat Image
01_Poland_Defensive_universal_learning_2005.pdf263.3 kBAdobe PDF    Request a copy

Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  17 November 2022/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator