|
|
 | | From: | Redistributed | | Subject: | JMLR: Stability of Randomized Learning Algorithms | | Date: | Thu, 20 Jan 2005 18:54:17 GMT |
|
|
 | [[Redistributed from JMLR announce]]
~From: elm@cs.umass.edu
~Date: Sun, 9 Jan 2005 14:06:32 -0500
~Subject: [Jmlr-announce] Stability of Randomized Learning Algorithms
The Journal of Machine Learning Research (www.jmlr.org) is pleased to
announce publication of a new paper:
------------------------------------------------------------------------
-------
Stability of Randomized Learning Algorithms
Andre Elisseeff, Theodoros Evgeniou and Massimiliano Pontil
JMLR 6 (Jan): 55--79, 2005
Abstract
We extend existing theory on stability, namely how much changes in the
training data influence the estimated models, and generalization
performance of deterministic learning algorithms to the case of
randomized algorithms. We give formal definitions of stability for
randomized algorithms and prove non-asymptotic bounds on the difference
between the empirical and expected error as well as the leave-one-out
and expected error of such algorithms that depend on their random
stability. The setup we develop for this purpose can be also used for
generally studying randomized learning algorithms. We then use these
general results to study the effects of bagging on the stability of a
learning method and to prove non-asymptotic bounds on the predictive
performance of bagging which have not been possible to prove with the
existing theory of stability for deterministic learning algorithms.
------------------------------------------------------------------------
------
This paper and previous papers are available electronically at
http://www.jmlr.org in PDF format. The papers of Volumes 1-4 were also
published in hardcopy by MIT Press; please see
http://mitpress.mit.edu/JMLR for details. Volume 5 and subsequent
volumes will be printed in hardcopy by Microtome Publishing. Please see
http://www.mtome.com/Publications/jmlr.html for details and ordering
information.
-Erik G. Learned-Miller
elm@cs.umass.edu
_______________________________________________
Jmlr-announce mailing list
Jmlr-announce@lists.csail.mit.edu
http://lists.csail.mit.edu/mailman/listinfo/jmlr-announce
[ comp.ai is moderated. To submit, just post and be patient, or if ]
[ that fails mail your article to , and ]
[ ask your news administrator to fix the problems with your system. ]
|
|
|
