Years and Authors of Summarized Original Work
1993; Kearns, Li
1999; Cesa-Bianchi, Dichterman, Fischer, Shamir, Simon
Problem Definition
This problem is concerned with PAC learning of concept classes when training examples are affected by malicious errors. The PAC (probably approximately correct) model of learning (also known as the distribution-free model of learning) was introduced by Valiant [13]. This model makes the idealized assumption that error-free training examples are generated from the same distribution which is then used to evaluate the learned hypothesis. In many environments, however, there is some chance that an erroneous example is given to the learning algorithm. The malicious noise model – again introduced by Valiant [14] – extends the PAC model by allowing example errors of any kind: it makes no assumptions on the nature of the errors that occur. In this sense the malicious noise model is a worst-case model of errors, in which errors may be generated by an...
Recommended Reading
Aslam JA, Decatur SE (1998) Specification and simulation of statistical query algorithms for efficiency and noise tolerance. J Comput Syst Sci 56:191–208
Auer P, Cesa-Bianchi N (1998) On-line learning with malicious noise and the closure algorithm. Ann Math Artif Intell 23:83–99
Ben-David S, Eiron N, Long P (2003) On the difficulty of approximately maximizing agreements. J Comput Syst Sci 66:496–514
Blumer A, Ehrenfeucht A, Haussler D, Warmuth M (1989) Learnability and the Vapnik-Chervonenkis dimension. J ACM 36:929–965
Brubaker SC (2009) Robust PCA and clustering in noisy mixtures. In: Proceedings of 20th annual ACM-SIAM symposium on discrete algorithms, New York, pp 1078–1087
Bshouty N, Eiron N, Kushilevitz E (2002) PAC learning with nasty noise. Theor Comput Sci 288:255–275
Cesa-Bianchi N, Dichterman E, Fischer P, Shamir E, Simon HU (1999) Sample-efficient strategies for learning in the presence of noise. J ACM 46:684–719
Kearns M, Li M (1988) Learning in the presence of malicious errors. In: Proceedings of 20th ACM symposium on theory of computing, Chicago, pp 267–280
Kearns M, Li M (1993) Learning in the presence of malicious errors. SIAM J Comput 22:807–837
Kearns M, Schapire R, Sellie L (1994) Toward efficient agnostic learning. Mach Learn 17:115–141
Klivans AR, Long PM, Servedio RA (2009) Learning halfspaces with malicious noise. Journal of Mach Learn Res 10:2715–2740
Servedio RA (2003) Smooth boosting and learning with malicious noise. Journal of Mach Learn Res 4:633–648
Valiant L (1984) A theory of the learnable. Commun ACM 27:1134–1142
Valiant L Learning (1985) disjunctions of conjunctions. In: Proceedings of 9th international joint conference on artificial intelligence, Los Angeles, pp 560–566
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer Science+Business Media New York
About this entry
Cite this entry
Auer, P. (2015). Learning with Malicious Noise. In: Kao, MY. (eds) Encyclopedia of Algorithms. Springer, Boston, MA. https://doi.org/10.1007/978-3-642-27848-8_198-2
Download citation
DOI: https://doi.org/10.1007/978-3-642-27848-8_198-2
Received:
Accepted:
Published:
Publisher Name: Springer, Boston, MA
Online ISBN: 978-3-642-27848-8
eBook Packages: Springer Reference Computer SciencesReference Module Computer Science and Engineering