Lower Bounds for the Empirical Minimization Algorithm
Download (332.03 kB)
-
Altmetric Citations
Description
In this correspondence, we present a simple argument that proves that under mild geometric assumptions on the class F and the set of target functions Τ, the empirical minimization algorithm cannot yield a uniform error rate that is faster than 1√k in t
Collections | ANU Research Publications |
---|---|
Date published: | 2008 |
Type: | Journal article |
URI: | http://hdl.handle.net/1885/31331 |
Source: | IEEE Transactions on Information Theory |
DOI: | 10.1109/TIT.2008.926323 |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
01_Mendelson_Lower_Bounds_for_the_Empirical_2008.pdf | 332.03 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