Towards robust model selection using estimation and approximation error bounds

Subscribe (Full Service)


	Search: The ACM Digital Library The Guide

	Feedback

Towards robust model selection using estimation and approximation error bounds

Full text

Pdf (1.21 MB)

Source

Annual Workshop on Computational Learning Theory archive
Proceedings of the ninth annual conference on Computational learning theory table of contents

Desenzano del Garda, Italy

Pages: 57 - 67

Year of Publication: 1996

ISBN:0-89791-811-8

Authors

Joel Ratsaby	Department of Electrical Engineering, Technion, Haifa 32000, Israel
Ronny Meir	Department of Electrical Engineering, Technion, Haifa 32000, Israel
Vitaly Maiorov	Department of Mathematics, Technion, Haifa 32000, Israel

Sponsors

Univ degli Studi de Milano : Universite degli Studi de Milano
SIGACT: ACM Special Interest Group on Algorithms and Computation Theory
SIGART: ACM Special Interest Group on Artificial Intelligence

Publisher

ACM New York, NY, USA

Bibliometrics

Downloads (6 Weeks): 0, Downloads (12 Months): 7, Citation Count: 1

Additional Information:

references cited by index terms collaborative colleagues peer to peer

Tools and Actions:	Request Permissions Review this Article Save this Article to a Binder Display Formats: BibTeX EndNote ACM Ref

DOI Bookmark:	Use this link to bookmark this Article: http://doi.acm.org/10.1145/238061.238069 What is a DOI?

REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

	1	R. A. Adams, Sobolev Spaces, Academic Press, 1975.
	2	A.N. Arkhangel'skii, "Lower bounds for probabilities of large deviations for sums of independent random variables", Theory Prob. Appl., vol. 34, no. 4, 1989.
	3	Andrew R. Barron, Approximation and Estimation Bounds for Artificial Neural Networks, Machine Learning, v.14 n.1, p.115-133, Jan. 1994 [doi>10.1023/A:1022650905902]
	4	J.M. Bernardo and A.F.M. Smith, Bayeszan Theory, John Wiley, 1994.
	5	S. Geisser, Predictive Inference: An Introductzon~ Chapman & Hall, 1993.
	6	David Haussler, Decision theoretic generalizations of the PAC model for neural net and other learning applications, Information and Computation, v.100 n.1, p.78-150, Sept. 1992 [doi>10.1016/0890-5401(92)90010-D]
	7	David Haussler , H. Sebastian Seung , Michael Kearns , Naftali Tishby, Rigorous learning curve bounds from statistical mechanics, Proceedings of the seventh annual conference on Computational learning theory, p.76-87, July 12-15, 1994, New Brunswick, New Jersey, United States [doi>10.1145/180139.181018]
	8	Marek Karpinski , Angus Macintyre, Polynomial bounds for VC dimension of sigmoidal neural networks, Proceedings of the twenty-seventh annual ACM symposium on Theory of computing, p.200-208, May 29-June 01, 1995, Las Vegas, Nevada, United States [doi>10.1145/225058.225118]
	9	Michael Kearns , Yishay Mansour , Andrew Y. Ng , Dana Ron, An experimental and theoretical comparison of model selection methods, Proceedings of the eighth annual conference on Computational learning theory, p.21-30, July 05-08, 1995, Santa Cruz, California, United States [doi>10.1145/225298.225301]
	10	Moshe Leshno , Vladimir Ya. Lin , Allan Pinkus , Shimon Schocken, Multilayer feedforward networks with a nonpolynomial activation function can approximate any function, Neural Networks, v.6 n.6, p.861-867, 1993 [doi>10.1016/S0893-6080(05)80131-5]
	11	G. Lugosi and K. Zeger, "Concept learning using complexity regularization", IEEE Trans. Inf. Theory, vol. 42, no. 1, pp. 48-54, 1996.
	12	G. Lugosi and A.B. Nobel "Adaptive model selection using empirical complexities" preprint, 1996.
	13	Vitaly Maiorov, Linear widths of function spaces equipped with the Gaussian measure, Journal of Approximation Theory, v.77 n.1, p.74-88, April 1994 [doi>10.1006/jath.1994.1035]
	14	H. N. Mhaskar, Neural networks for optimal approximation of smooth and analytic functions, Neural Computation, v.8 n.1, p.164-177, Jan. 1996
	15	S. M. Nikolski, "Approximation of the Many Variables Functions and Theorems of Embedding", Nauka, Moscow, 1969.
	16	Pollard D., Convergence of Stochastzc Processes, Springer Series in Statistics, (1984).
	17	J. Ratsaby, R. Meir, "Finite Sample Size Results for Robust Model Selection; Application to Neural Networks", October 1995, Technical Report, Dept. E.E., Technion, Publication # CC-117.
	18	Jorma Rissanen, Stochastic Complexity in Statistical Inquiry Theory, World Scientific Publishing Co., Inc., River Edge, NJ, 1989
	19	A. N. Shiryayev, Probability, Springer-Verlag, Berlin 1984.
	20	M. Stone, "Cross-validation choice and assessment of statistical predictionss", J. Royal. Stat~s. Soc, vol. B36, pp. 111-147, 1974.
	21	H. Triebel, Theory of~unctzon Spaces, Birkhauser, Basel 1983.
	22	Vladimir Vapnik, Estimation of Dependences Based on Empirical Data: Springer Series in Statistics (Springer Series in Statistics), Springer-Verlag New York, Inc., Secaucus, NJ, 1982
	23	V.N. Vapnik and A.Y. Chernovenkins, "On the uniform convergence of relative frequencies of events to their probabilities", Theory of Prob. and Applic., vol. 16 no. 2, pp. 264-280, 1971.
	24	H.E. Warren, "Lower bounds for approximation by non-linear manifolds", Trans. of the AMS, vol. 133, pp. 167-178, 1968.
	25	H. White, Estzmatzon, Inference and Speczficahon Analys~s, Cambridge university press, 1994.
	26	A. Zygmund, Trigonometric Seines, Cambridge university press, 1968.