Abstract
We investigate the use of certain data-dependent estimates of the complexity of a function class, called Rademacher and gaussian complexities. In a decision theoretic setting, we prove general risk bounds in terms of these complexities. We consider function classes that can be expressed as combinations of functions from basis classes and show how the Rademacher and gaussian complexities of such a function class can be bounded in terms of the complexity of the basis classes.We give examples of the application of these techniques in finding data-dependent risk bounds for decision trees, neural networks and support vector machines.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Peter L. Bartlett. The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network. IEEE Transactions on Information Theory, 44(2):525–536, 1998.
Peter L. Bartlett, Stéphane Boucheron, and Gábor Lugosi. Model selection and error estimation. Machine Learning, 2001. (To appear).
Mostefa Golea, Peter L. Bartlett, and Wee Sun Lee. Generalization in decision trees and DNF: Does size matter? In NIPS 10, pages 259–265, 1998.
Michael J. Kearns, Yishay Mansour, Andrew Y. Ng, and Dana Ron. An experimental and theoretical comparison of model selection methods. Machine Learning, 27:7–50, 1997.
V. Koltchinskii. Rademacher penalties and structural risk minimization. Technical report, Department of Mathematics and Statistics, University of New Mexico, 2000.
V. Koltchinskii and D. Panchenko. Empirical margin distributions and bounding the generalization error of combined classifiers. Technical report, Department of Mathematics and Statistics, University of New Mexico, 2000.
V. Koltchinskii and D. Panchenko. Rademacher processes and bounding the risk of function learning. Technical report, Department of Mathematics and Statistics, University of New Mexico, 2000.
E.B. Kong and T.G. Dietterich. Error-correcting output coding corrects bias and variance. In Proc. 12th International Conference on Machine Learning, pages 313–321. Morgan Kaufmann, 1995.
M. Ledoux and M. Talagrand. Probability in Banach Spaces: isoperimetry and processes. Springer, 1991.
Llew Mason, Peter L. Bartlett, and Jonathan Baxter. Improved generalization through explicit optimization of margins. Machine Learning, 38(3):243–255, 2000.
C. McDiarmid. On the method of bounded differences. In Surveys in Combinatorics 1989, pages 148–188. Cambridge University Press, 1989.
Shahar Mendelson. l-norm and its application to learning theory. Positivity, 2001. (To appear—see http://www.axiom.anu.edu.au/~shahar).
Shahar Mendelson. Rademacher averages and phase transitions in Glivenko-Cantelli classes. (see http://www.axiom.anu.edu.au/~shahar), 2001.
Shahar Mendelson. Some remarks on covering numbers. (unpublished manuscript—see http://www.axiom.anu.edu.au/~shahar), 2001.
G. Pisier. The volume of convex bodies and Banach space geometry. Cambridge University Press, 1989.
Robert E. Schapire. Using output codes to boost multiclass learning problems. In Machine Learning: Proc. Fourteenth International Conference, pages 313–321, 1997.
Robert E. Schapire, Yoav Freund, Peter L. Bartlett, and Wee Sun Lee. Boosting the margin: a new explanation for the effectiveness of voting methods. Annals of Statistics, 26(5):1651–1686, October 1998.
John Shawe-Taylor, Peter L. Bartlett, Robert C. Williamson, and Martin Anthony. Structural risk minimisation over data-dependent hierarchies. IEEE Transactions on Information Theory, 44(5):1926–1940, 1998.
N. Tomczak-Jaegermann. Banach-Mazur distance and finite-dimensional operator ideals. Number 38 in Pitman Monographs and Surveys in Pure and Applied Mathematics. Pitman, 1989.
Vladimir N. Vapnik and A.Y. Chervonenkis. On the uniform convergence of relative frequencies of events to their probabilities. Theory of Probability and its Applications, 16(2):264–280, 1971.
R.C. Williamson, A.J. Smola, and B. Schölkopf. Generalization performance of regularization networks and support vector machines via entropy numbers of compact operators. IEEE Transactions on Information Theory, 2001. (To appear).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bartlett, P.L., Mendelson, S. (2001). Rademacher and Gaussian Complexities: Risk Bounds and Structural Results. In: Helmbold, D., Williamson, B. (eds) Computational Learning Theory. COLT 2001. Lecture Notes in Computer Science(), vol 2111. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44581-1_15
Download citation
DOI: https://doi.org/10.1007/3-540-44581-1_15
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42343-0
Online ISBN: 978-3-540-44581-4
eBook Packages: Springer Book Archive