Abstract
We provide a new representation-independent formulation of Occam’s razor theorem, based on Kolmogorov complexity. This new formulation allows us to:
-
Obtain better sample complexity than both length-based [4] and VC-based [3] versions of Occam’s razor theorem, in many applications.
-
Achieve a sharper reverse of Occam’s razor theorem than that of [5]. Specifically, we weaken the assumptions made in [5] and extend the reverse to superpolynomial running times.
Supported in part by the NSERC Operating Grant OGP0046506, ITRC, and NSF-ITR Grant 0085801 at UCSB.
Partially supported by an NSERC International Fellowship and ITRC.
Partially supported by the European Community through NeuroCOLT ESPRIT Working Group Nr. 8556. Affiliated with CWI and the University of Amsterdam.
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
M. Anthony and N. Biggs, Computational Learning Theory, Cambridge University Press, 1992.
A. Blum, T. Jiang, M. Li, J. Tromp, M. Yannakakis, Linear approximation of shortest common superstrings. Journal ACM, 41:4 (1994), 630–647.
A. Blumer and A. Ehrenfeucht and D. Haussler and M. Warmuth, Learnability and the Vapnik-Chervonenkis Dimension. J. Assoc. Comput. Mach., 35(1989), 929–965.
A. Blumer and A. Ehrenfeucht and D. Haussler and M. Warmuth, Occam’s Razor. Inform. Process. Lett., 24(1987), 377–380.
R. Board and L. Pitt, On the necessity of Occam Algorithms. 1990 STOC, pp. 54–63.
A. Ehrenfeucht, D. Haussler, M. Kearns, L. Valiant. A general lower bound on the number of examples needed for learning. Inform. Computation, 82(1989), 247–261.
D. Haussler. Quantifying inductive bias: AI learning algorithms and Valiant’s learning framework. Artificial Intelligence, 36:2(1988), 177–222.
D. Haussler, N. Littlestone, and, M. Warmuth. Predicting {0,1}-functions on randomly drawn points. Information and Computation, 115:2(1994), 248–292.
T. Jiang and M. Li, DNA sequencing and string learning, Math. Syst. Theory, 29(1996), 387–405.
M. Li. Towards a DNA sequencing theory. 31st IEEE Symp. on Foundations of Comp. Sci., 125–134, 1990.
M. Li and P. Vitányi. An Introduction to Kolmogorov Complexity and Its Applications. 2nd Edition, Springer-Verlag, 1997.
L. G. Valiant. A Theory of the Learnable. Comm. ACM, 27(11), 1134–1142, 1984.
M.K. Warmuth. Towards representation independence in PAC-learning. In AII-89, pp. 78–103, 1989.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, M., Tromp, J., Vitányi, P. (2002). Sharpening Occam’s Razor. In: Ibarra, O.H., Zhang, L. (eds) Computing and Combinatorics. COCOON 2002. Lecture Notes in Computer Science, vol 2387. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45655-4_44
Download citation
DOI: https://doi.org/10.1007/3-540-45655-4_44
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43996-7
Online ISBN: 978-3-540-45655-1
eBook Packages: Springer Book Archive