Rocco A. Servedio  Home/Search
Context
Related
| harvard.edu/~rocco/Public/lnh.ps 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: harvard.edu/~rocco/papers (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: We describe a PAC algorithm for learning linear threshold functions when some fraction of the examples used for learning are generated and labeled by an omniscient malicious adversary. The algorithm has complexity bounds similar to the classical Perceptron algorithm but can tolerate a substantially higher level of malicious noise than Perceptron and thus may be of significant practical interest. At the heart of our algorithm is a new boosting procedure which is guaranteed to generate only... (Update)
Active bibliography (related documents): More All
1.0: Smooth Boosting and Learning with Malicious Noise - Servedio (2003) (Correct)
1.0: PAC Analogues of Perceptron and Winnow via Boosting the Margin - Servedio (2000) (Correct)
0.4: Learning DNF in Time ... - Klivans, Servedio (2001) (Correct)
Similar documents based on text: More All
0.7: Boosting in the Presence of Noise - Kalai, Servedio (2002) (Correct)
0.2: New Degree Bounds for Polynomial Threshold Functions - O'Donnell, Servedio (Correct)
0.2: Learning with noise. Extension to regression. - Teytaud (2001) (Correct)
BibTeX entry: (Update)
@misc{ servedio-smooth,
author = "Rocco A. Servedio",
title = "Smooth Boosting and Linear Threshold Learning with Malicious Noise",
url = "citeseer.ist.psu.edu/358573.html" }
Citations (may not include all citations):537 A theory of the learnable (context) - Valiant - 1984
509 A decision-theoretic generalization of on-line learning and .. - Freund, Schapire - 1997
465 Learnability and the Vapnik-Chervonenkis Dimension (context) - Blumer, Ehrenfeucht et al. - 1989
441 Queries and concept learning (context) - Angluin - 1988
317 Learning quickly when irrelevant attributes abound: A new li.. (context) - Littlestone - 1988
248 An introduction to computational learning theory (context) - Kearns, Vazirani - 1994
174 Principles of neurodynamics (context) - Rosenblatt - 1962
134 An experimental comparison of three methods for constructing.. - Dietterich
94 Learning in the presence of malicious errors - Kearns, Li - 1993
63 Generalization performance of support vector machines and ot.. - Bartlett, Shawe-Taylor - 1999
50 Large margin classification using the perceptron algorithm - Freund, Schapire - 1998
44 Fat-shattering and the learnability of real-valued functions - Bartlett, Long et al. - 1996
42 Hard-core distributions for somewhat hard problems - Impagliazzo - 1995
37 Statistical queries and faulty PAC oracles - Decatur - 1993
32 A short introduction to boosting - Freund, Schapire - 1999
32 The perceptron: a model for brain functioning (context) - Block - 1962
25 Theoretical views of boosting - Schapire - 1999
22 On convergence proofs on perceptrons (context) - Novikoff - 1962
20 Recent results on boolean concept learning - Kearns, Li et al. - 1987
19 Learning noisy perceptrons by a perceptron in polynomial tim.. (context) - Cohen - 1997
17 Specification and simulation of statistical query algorithms.. - Aslam, Decatur - 1998
12 The perceptron algorithm is fast for nonmalicious distributi.. (context) - Baum - 1990
12 Boosting and hard-core sets - Klivans, Servedio - 1999
7 and a perceptron-like algorithm (context) - Servedio, learning et al. - 1999
5 Identification criteria and lower bounds for perceptron-like.. - Schmitt - 1998
3 Sample-efficient strategies for learning in the presence of .. (context) - Cesa-Bianchi, Dichterman et al. - 1999
3 line learning with malicious noise and the closure algorithm - Auer, Cesa-Bianchi - 1998
2 The perceptron algorithm versus winnow: linear vs (context) - Kivinen, Warmuth et al. - 1995
2 Learning conjunctions with noise under product distributions (context) - Mansour, Parnas - 1998
1 Learning nested differences in the presence of malicious noi.. - Auer - 1997
1 Proc. 13th Conf. on Comp. Learning Theory (context) - Servedio, of et al. - 2000
Documents on the same site (http://www.deas.harvard.edu/~rocco/papers.html): More
Gene Structure Prediction From Many Attributes - Deaton, Servedio (1998) (Correct)
Probabilistic Construction of Monotone Formulae for.. - Rocco Servedio Division (Correct)
Learning DNF in Time ... - Klivans, Servedio (2001) (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