Defensive universal learning with experts
-
Altmetric Citations
Description
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. From this, we obtain a master algorithm for “reactive” experts problems, which...[Show more]
Collections | ANU Research Publications |
---|---|
Date published: | 2005 |
Type: | Conference paper |
URI: | http://hdl.handle.net/1885/15047 |
Book Title: | Algorithmic Learning Theory: 16th International Conference, ALT 2005, Singapore, October 8-11, 2005. Proceedings |
DOI: | 10.1007/11564089_28 |
Access Rights: | Open Access |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
Poland and Hutter Defensive Universal Learning 2005.pdf | 249.15 kB | Adobe PDF |
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