The importance of convexity in learning with squared loss

Subscribe (Full Service)


	Search: The ACM Digital Library The Guide

	Feedback

The importance of convexity in learning with squared loss

Full text

Pdf (667 KB)

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: 140 - 146

Year of Publication: 1996

ISBN:0-89791-811-8

Authors

Wee Sun Lee	Electrical Engineering Department, University College UNSW, Australian Defence Force Academy, Canberra, ACT 2600, Australia
Peter L. Bartlett	Dept. of Systems Engineering, RSISE, Aust. National University, Canberra, ACT 0200, Australia
Robert C. Williamson	Department of Engineering, Australian National University, Canberra, ACT 0200, Australia

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): 16, Downloads (12 Months): 26, Citation Count: 1

Additional Information:

references cited by index terms collaborative colleagues

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/10.1145/238061.238082 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	Martin Anthony , Norman Biggs, Computational learning theory: an introduction, Cambridge University Press, New York, NY, 1992
	2	A.R. Barron. Complexity regularization with applications to artificial neural networks. In G. Roussa, editor, Nonparametric Functional Estimation, pages 561- 576. Kluwer Academic, Boston, MA and Dordrecht, the Netherlands, 1990.
	3	A.R. Barron. Neural net approximation. In Proc. 7th Yale Workshop on Adaptive and Learning Systems, 1992.
	4	A.R. Barron. Universal approximation bounds for superposition of a sigmoidal function. IEEE Trans. on Information Theory, 39:930-945, 1993.
	5	Keinosuke Fukunaga, Introduction to statistical pattern recognition (2nd ed.), Academic Press Professional, Inc., San Diego, CA, 1990
	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	Michael J. Kearns , Robert E. Schapire , Linda M. Sellie, Toward Efficient Agnostic Learning, Machine Learning, v.17 n.2-3, p.115-141, Nov./Dec. 1994 [doi>10.1007/BF00993468]
	8	W. S. Lee, P. L. Bartlett, and R. C. Williamson. Efficient agnostic learning of neural networks with bounded fanin. Technical report, Department of Systems Engineering, Australian National University, 1994. To appear in IEEE Trans. on Information Theory.
	9	Wee Sun Lee , Peter L. Bartlett , Robert C. Williamson, On efficient agnostic learning of linear combinations of basis functions, Proceedings of the eighth annual conference on Computational learning theory, p.369-376, July 05-08, 1995, Santa Cruz, California, United States [doi>10.1145/225298.225343]
	10	Wolfgang Maass, Agnostic PAC learning of functions on analog neural nets, Neural Computation, v.7 n.5, p.1054-1078, Sept. 1995 [doi>10.1162/neco.1995.7.5.1054]
	11	Daniel F. McCaffrey , A. Ronald Gallant, Convergence rates for single hidden layer feedforward networks, Neural Networks, v.7 n.1, p.147-158, 1994 [doi>10.1016/0893-6080(94)90063-9]
	12	D. Pollard. Convergence of Stochastic Processes. Springer-Verlag, Berlin, 1984.
	13	D. Pollard. Uniform ratio limit theorems for empirical processes. Submitted to Scandinavian Journal of Statistics, 1995.