Michael Kearns ATT Bell Laboratories Ming Li University of Waterloo  Home/Search
Context Related
| upenn.edu/~mkearns/pap...malicious.ps.Z Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: upenn.edu/~mkearns/ (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: In this paper we study an extension of the distribution-free model of learning introduced by Valiant [23] (also known as the probably approximately correct or PAC model) that allows the presence of malicious errors in the examples given to a learning algorithm. Such errors are generated by an adversary with unbounded computational power and access to the entire history of the learning algorithm's computation. Thus, we study a worst-case model of errors. (Update)
Similar documents based on text: More All
0.4: Learning in the Presence of Malicious Errors - Kearns (1993) (Correct)
0.1: Learning with noise. Extension to regression. - Teytaud (2001) (Correct)
0.1: of Machine Learning - Michael Kearns The (1994) (Correct)
BibTeX entry: (Update)
Michael Kearns and Ming Li. Learning in the presence of malicious errors. SIAM Journal on Computing, 22(4):807--837, August 1993. http://citeseer.ist.psu.edu/kearns93learning.html More
@inproceedings{ kearns88learning,
author = "Michael Kearns and Ming Li",
title = "Learning in the presence of malicious errors",
pages = "267--280",
year = "1988",
url = "citeseer.ist.psu.edu/kearns93learning.html" }
Citations (may not include all citations):4212 Computers and intractability: a guide to the theory of NP-co.. (context) - Garey, Johnson - 1979
465 Learnability and the Vapnik-Chervonenkis dimension (context) - Blumer, Ehrenfeucht et al. - 1989
293 Approximation algorithms for combinatorial problems (context) - Johnson - 1974
245 A measure of asymptotic efficiency for tests of a hypothesis.. (context) - Chernoff - 1952
151 A general lower bound on the number of examples needed for l.. (context) - Ehrenfeucht, Haussler et al. - 1989
149 Information Processing Letters (context) - Blumer, Ehrenfeucht et al. - 1987
142 Learning from noisy examples (context) - Angluin, Laird - 1988
139 A greedy heuristic for the set covering problem (context) - Chvatal - 1979
132 Fast probabilistic algorithms for Hamiltonian circuits and m.. (context) - Angluin, Valiant - 1979
94 Learning in the presence of malicious errors - Kearns, Li - 1988
81 Equivalence of models for polynomial learnability (context) - Haussler, Kearns et al.
78 the learnability of Boolean formulae - Kearns, Li et al. - 1987
36 A polynomial-time algorithm for learning k-variable pattern .. (context) - Kearns, Pitt
2 Learning in an infinite attribute space (context) - Blum - 1990
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.cis.upenn.edu/~mkearns/): More
Graphical Economics - Sham Kakade Michael (Correct)
Efficient Algorithms for Learning to Play Repeated Games Against.. - al. (1995) (Correct)
On the Boosting Ability of Top-Down Decision Tree Learning.. - Kearns (1996) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC