# On-line learning with malicious noise and the closure algorithm

## Abstract

We investigate a variant of the on-line learning model for classes of \0,1\-valued functions (concepts) in which the labels of a certain amount of the input instances are corrupted by adversarial noise. We propose an extension of a general learning strategy, known as “Closure Algorithm”, to this noise model, and show a worst-case mistake bound of m + (d+1)K for learning an arbitrary intersection-closed concept class C, where K is the number of noisy labels, d is a combinatorial parameter measuring C's complexity, and m is the worst-case mistake bound of the Closure Algorithm for learning C in the noise-free model. For several concept classes our extended Closure Algorithm is efficient and can tolerate a noise rate up to the information-theoretic upper bound. Finally, we show how to efficiently turn any algorithm for the on-line noise model into a learning algorithm for the PAC model with malicious noise.

## Keywords

Boolean Function Concept Class Target Class Noise Rate Hypothesis Class## Preview

Unable to display preview. Download preview PDF.

## References

- [1]D. Angluin, Queries and concept learning, Machine Learning 2(4) (1988) 319–342.Google Scholar
- [2]M. Anthony and J. Shawe-Taylor, A result of Vapnik with applications, Discrete Applied Mathematics 47 (1994) 207–217.MathSciNetCrossRefGoogle Scholar
- [3]P. Auer, On-line learning of rectangles in noisy environments, in:
*Proceedings of the 6th Annual ACM Workshop on Computational Learning Theory*(ACM Press, 1993) pp. 253–261.Google Scholar - [4]P. Auer and P.M Long, Simulating access to hidden information while learning, in:
*Proceedings of the 26th ACM Symposium on the Theory of Computing*(ACM Press, 1994) pp. 263–272.Google Scholar - [5]S. Boucheron, Learnability from positive examples in the Valiant framework, Manuscript (1988).Google Scholar
- [6]N. Cesa-Bianchi, Models of learning with noise, Unpublished manuscript (1994).Google Scholar
- [7]N. Cesa-Bianchi, Y. Freund, D.P. Helmbold and M.K. Warmuth, On-line prediction and conversion strategies, in:
*Proceedings of the First Euro-COLT Workshop*, The Institute of Mathematics and its Applications Conference Series – New Series Number 53 (Clarendon Press, Oxford, 1994) pp. 205–216.Google Scholar - [8]Z. Chen and S. Homer, On learning counting functions with queries, in:
*Proceedings of the 7th Annual ACM Workshop on Computational Learning Theory*(ACM Press, 1994) pp. 218–227.Google Scholar - [9]P. Fischer and H.U. Simon, On learning ring-sum-expansions, SIAM Journal on Computing 21 (1992) 181–192.zbMATHMathSciNetCrossRefGoogle Scholar
- [10]D. Haussler, N. Littlestone and M.K. Warmuth, Predicting 0, 1-functions on randomly drawn points, Information and Computation 115(2) (1994) 248–292.zbMATHMathSciNetCrossRefGoogle Scholar
- [11]D.P. Helmbold and P.M Long, Tracking drifting concepts by minimizing disagreements, Machine Learning 14(1) (1994) 27–45.zbMATHGoogle Scholar
- [12]D.P. Helmbold, R. Sloan and M.K. Warmuth, Learning nested differences of intersection-closed concept classes, Machine Learning 5(2) (1990) 165–196.Google Scholar
- [13]D.P. Helmbold, R. Sloan and M.K. Warmuth, Learning integer lattices, SIAM Journal on Computing 21(2) (1992) 240–266.zbMATHMathSciNetCrossRefGoogle Scholar
- [14]M.J. Kearns and M. Li, Learning in the presence of malicious errors, SIAM Journal on Computing 22(4) (1993) 807–837.zbMATHMathSciNetCrossRefGoogle Scholar
- [15]N. Littlestone, Learning quickly when irrelevant attributes abound: a new linear-threshold algorithm, Machine Learning 2(4) (1988) 285–318.Google Scholar
- [16]N. Littlestone, Mistake bounds and logarithmic linear-threshold learning algorithms, Ph.D. thesis, University of California at Santa Cruz (1989).Google Scholar
- [17]N. Littlestone and M.K. Warmuth, The weighted majority algorithm,
*Information and Computation*108 (1994) 212–261.zbMATHMathSciNetCrossRefGoogle Scholar - [18]B.K. Natarajan, On learning boolean functions, in:
*Proceedings of the 19th ACM Symposium on the Theory of Computing*(ACM Press, 1987) pp. 296–304.Google Scholar - [19]B.K. Natarajan,
*Machine Learning: A Theoretical Approach*(Morgan Kaufmann, San Mateo, CA, 1991).Google Scholar - [20]A. Schrijver,
*Theory of Linear and Integer Programming*(Wiley, New York, 1986).Google Scholar - [21]L. Valiant, A theory of the learnable, Communications of the ACM 27(11) (1984) 1134–1142.zbMATHCrossRefGoogle Scholar