Nicolò Cesa-Bianchi, Eli Dichterman, Paul Fischer, Eli Shamir, Hans Ulrich Simon  Home/Search
Context
Related
| neurocolt.org/tech_reps/1...99035.ps.gz 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: neurocolt.org/tech_reps/1999/ (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: In this paper we prove various results about PAC learning in the presence of malicious noise. Our main interest is the sample size behaviour of learning algorithms. We prove the first nontrivial sample complexity lower bound in this model by showing that order of "=\Delta 2 + d=\Delta (up to logarithmic factors) examples are necessary for PAC learning any target class of f0; 1g-valued functions of VC dimension d, where " is the desired accuracy and j = "=(1 + ") \Gamma \Delta the... (Update)
Similar documents (at the sentence level):
61.0%: Sample-efficient Strategies for Learning in the.. - Cesa-Bianchi.. (1999) (Correct)
Active bibliography (related documents): More All
0.2: Toward a usable theory of Chernoff Bounds for heterogeneous and.. - Siegel (1992) (Correct)
0.1: PAC Learning with Nasty Noise - Bshouty, Eiron, Kushilevitz (1999) (Correct)
0.1: Noise Tolerant Algorithms for Learning and Searching - Aslam (1995) (Correct)
Similar documents based on text: More All
1.0: Learning via Internal Representation (Extended Abstract) - Dichterman (1998) (Correct)
0.9: Adaptive and Self-Confident On-Line Learning Algorithms - Auer, Cesa-Bianchi, Gentile (2000) (Correct)
0.8: On Restricted-Focus-of-Attention Learnability of Boolean Functions - Birkendorf (1998) (Correct)
BibTeX entry: (Update)
@article{ cesabianchi99sampleefficient,
author = "Nicol{\`o} Cesa-Bianchi and Eli Dichterman and Paul Fischer and Eli Shamir and Hans Ulrich Simon",
title = "Sample-efficient strategies for learning in the presence of noise",
journal = "Journal of the ACM",
volume = "46",
number = "5",
pages = "684--719",
year = "1999",
url = "citeseer.ist.psu.edu/article/cesa-bianchi99sampleefficient.html" }
Citations (may not include all citations):493 Communications of the ACM (context) - Valiant, of et al. - 1984
348 Estimation of Dependences Based on Empirical Data (context) - Vapnik - 1982
151 A general lower bound on the number of examples needed for l.. (context) - Ehrenfeucht, Haussler et al. - 1989
115 Efficient distribution-free learning of probabilistic concep.. - Kearns, Schapire - 1994
115 the Density of Families of Sets (context) - Sauer - 1972
102 Toward efficient agnostic learning - Kearns, Schapire et al. - 1994
94 Learning in the presence of malicious errors - Kearns, Li - 1993
52 Learning from good and bad data (context) - Laird - 1988
12 Stability and Order for Models and Theories in Infinitary La.. (context) - Shelah, Problem - 1972
9 General bounds on the number of examples needed for learning.. (context) - Simon - 1993
8 Some approximations to the binomial distribution function (context) - Bahadur - 1960
7 Monotone convergence of binomial probabilities and a general.. (context) - Jogdeo, Samuels - 1968
Documents on the same site (http://www.neurocolt.org/tech_reps/1999/): More
On the Sample Complexity for Nonoverlapping Neural Networks - Schmitt (Correct)
The consistency dimension and.. - Balcázar.. (1999) (Correct)
Dynamic Stochastic Synapses as Computational Units - Maass, Zador (1998) (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