Abstract
We consider the complexity of learning classes of smooth functions formed by bounding different norms of a function's derivative. The learning model is the generalization of the mistake-bound model to continuous-valued functions. Suppose Fq is the set of all absolutely continuous functions f from [0, 1] to R such that ∥f′∥q ≤1, and opt(Fq, m) is the best possible bound on the worst-case sum of absolute prediction errors over sequences of m trials. We show that for all q ≥ 2, opt(Fq, m)=Θ(√log m), and that opt(F2, m)=√log m/2 ±O(1).
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
D. Angluin. Queries and concept learning. Machine Learning, 2:319–342, 1988.
N. Cesa-Bianchi, P.M. Long, and M.K. Warmuth. Worst-case quadratic loss bounds for prediction using linear functions and gradient descent. IEEE Transactions on Neural Networks, 7(3):604–619, 1996.
V. Faber and J. Mycielski. Applications of learning theorems. Fundamenta Informaticae, 15(2):145–167, 1991.
D. Kimber and P.M. Long. On-line learning of smooth functions of a single variable. Theoretical Computer Science, 148(1):141–156, 1995.
G. Leitmann. The Calculus of Variations and Optimal Control. Plenum Press, 1981.
N. Littlestone. Learning quickly when irrelevant attributes abound: a new linearthreshold algorithm. Machine Learning, 2:285–318, 1988.
J. Mycielski. A learning algorithm for linear operators. Proceedings of the American Mathematical Society, 103(2):547–550, 1988.
H.L. Royden. Real Analysis. Macmillan, 1963.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Long, P.M. (1996). Improved bounds about on-line learning of smooth functions of a single variable. In: Arikawa, S., Sharma, A.K. (eds) Algorithmic Learning Theory. ALT 1996. Lecture Notes in Computer Science, vol 1160. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61863-5_31
Download citation
DOI: https://doi.org/10.1007/3-540-61863-5_31
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61863-8
Online ISBN: 978-3-540-70719-6
eBook Packages: Springer Book Archive