Abstract
We provide an algorithm to PAC learn multivariate polynomials with real coefficients. The instance space from which labeled samples are drawn is IRN but the coordinates of such samples are known only approximately. The algorithm is iterative and the main ingredient of its complexity, the number of iterations it performs, is estimated using the condition number of a linear programming problem associated to the sample. To the best of our knowledge, this is the first study of PAC learning concepts parameterized by real numbers from approximate data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Basu, S., R. POLLACK, and M.-F. Roy (1994). On the combinatorial and algebraic complexity of quantifier elimination. In 35th annual IEEE Symp. on Foundations of Computer Science, pp. 632–641.
Bergadano, F., N. Bshouty, and S. Varrichio (1996). Learning multivariate polynomials from substitutions and equivalence queries. Preprint.
Blumer, A., A. Ehrenfeucht, D. Haussler, and M. Warmuth (1989). Learnability and the vapnik-chervonenkis dimension. J. of the ACM 36, 929–965.
Cucker, F. (1999). Real computations with fake numbers. To appear in Proceedings of ICALP’99.
Goldberg, P. and M. Jerrum (1995). Bounding the Vapnik-Chervonenkis dimension of concept classes parameterized by real numbers. Machine Learning 18, 131–148.
Heintz, J., M.-F. Roy, and P. Solerno (1990). Sur la complexité du principe de Tarski-Seidenberg. Bulletin de la Société Mathématique de France 118, 101–126.
Kearns, M. and U. Vazirani (1994). An Introduction to Computational Learning Theory. The MIT Press.
Renegar, J. (1992). On the computational complexity and geometry of the first-order theory of the reals. Part I. Journal of Symbolic Computation 13, 255–299.
Renegar, J. (1995). Incorporating condition measures into the complexity theory of linear programming. SIAM Journal of Optimization 5, 506–524.
Schrijver, A. (1986). Theory of Linear and Integer Programming. John Wiley & Sons.
Shapire, R. and L. Sellie (1993). Learning sparse multivariate polynomials over a field with queries and counterexamples. In 6th ACM Workshop on Computational Learning Theory, pp. 17–26.
Smale, S. (1997). Complexity theory and numerical analysis. In A. Iserles (Ed.), Acta Numerica, pp. 523–551. Cambridge University Press.
Vavasis, S. and Y. Ye (1995). Condition numbers for polyhedra with real number data. Oper. Res. Lett. 17, 209–214.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cheung, D. (1999). Learning Real Polynomials with a Turing Machine. In: Watanabe, O., Yokomori, T. (eds) Algorithmic Learning Theory. ALT 1999. Lecture Notes in Computer Science(), vol 1720. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46769-6_19
Download citation
DOI: https://doi.org/10.1007/3-540-46769-6_19
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66748-3
Online ISBN: 978-3-540-46769-4
eBook Packages: Springer Book Archive