Relative loss bounds for multidimensional regression problems

Advances in Neural Information Processing Systems

Volumn , Issue , 1998, Pages 287-293

  Kivinen, Jyrki ^a   Warmuth, Manfred K ^b  

^a UNIVERSITY OF HELSINKI   (Finland)

^b University of California Santa Cruz   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS;

DISTANCE FUNCTIONS; GRADIENT DESCENT; LOSS FUNCTIONS; MULTIPLE OUTPUTS; ON-LINE UPDATES; OUTPUT NEURONS; PROBABILISTIC ASSUMPTIONS; REGRESSION PROBLEM;

TRANSFER FUNCTIONS;

EID: 0008969040     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. [Ama85] S. Amari. Differential Geometrical Methods in Statistics. Springer Verlag, Berlin, 1985.
2. [AHW95] P. Auer, M. Herbster, and M. K. Warmuth. Exponentially many local minima for single neurons. In Proc. 1995 Neural Information Processing Conference, pages 316-317. MIT Press, Cambridge, MA, November 1995.
3. [AW97] K. Azoury and M. K. Warmuth. Relative loss bounds and the exponential family of distributions. Unpublished manuscript, 1997.
4. [Bud93] M. Budinich. Some notes on perceptron learning. J. Phys. A.: Math. Gen., 26:4237-4247, 1993.
5. [CB97] N. Cesa-Bianchi. Analysis of two gradient-based algorithms for on-line regression. In Proc. 10th Annu. Conf. on Comput. Learning Theory, pages 163-170. ACM, 1997.
6. [Fos91] D. P. Foster. Prediction in the worst case. The Annals of Statistics, 19(2): 1084- 1090, 1991.
7. [GLS97] A. J. Grove, N. Littlestone, and D. Schuurmans. General convergence results for linear discriminant updates. In Proc. 10th Annu. Conf. on Comput. Learning Theory, pages 171-183. ACM, 1997.
8. [HKW95] D. P. Helmbold, J. Kivinen, and M. K. Warmuth. Worst-case loss bounds for sigmoided linear neurons. In Proc. Neural Information Processing Systems 1995, pages 309-315. MIT Press, Cambridge, MA, November 1995.
9. [JW98] A. K. Jagota and M. K. Warmuth. Continuous versus discrete-time nonlinear gradient descent: Relative loss bounds and convergence. Presented at Fifth Symposium on Artificial Intelligence and Mathematics, Ft. Lauderdale, FL, 1998.
10. [KW97] J. Kivinen and M. K. Warmuth. Additive versus exponentiated gradient updates for linear prediction. Information and Computation, 132(1): 1-64, January 1997.
11. [MN89] P. McCullagh and J. A. Nelder. Generalized Linear Models. Chapman & Hall, New York, 1989.
12. [Vov97] V. Vovk. Competitive on-line linear regression. In Proc. Neural Information Processing Systems 1997. MIT Press, Cambridge, MA, 1998.