论文信息 - The Competitive Complexity Ratio

The Competitive Complexity Ratio

The competitive complexity ratio is the worst case ratio of the regret of a data-driven model to that obtained by a model which benefits from side information. The side information bounds the sizes of unknown parameters. The ratio requires the use of a variation on parametric complexity, which we call the unconditional parametric complexity. We show that the optimal competitive complexity ratio is bounded and contrast this result with comparable results in statistics.

Dean P. Foster | R. Stine

[1] Peter Elias,et al. Universal codeword sets and representations of the integers , 1975, IEEE Trans. Inf. Theory.

[2] J. Rissanen. A UNIVERSAL PRIOR FOR INTEGERS AND ESTIMATION BY MINIMUM DESCRIPTION LENGTH , 1983 .

[3] I. Johnstone,et al. Ideal spatial adaptation by wavelet shrinkage , 1994 .

[4] Dean P. Foster,et al. The risk inflation criterion for multiple regression , 1994 .

[5] Jorma Rissanen,et al. Fisher information and stochastic complexity , 1996, IEEE Trans. Inf. Theory.

[6] Jorma Rissanen,et al. The Minimum Description Length Principle in Coding and Modeling , 1998, IEEE Trans. Inf. Theory.

[7] Jorma Rissanen,et al. Stochastic Complexity in Statistical Inquiry , 1989, World Scientific Series in Computer Science.

[8] Jorma Rissanen,et al. Hypothesis Selection and Testing by the MDL Principle , 1999, Comput. J..

[9] Dean P. Foster,et al. Local Asymptotic Coding and the Minimum Description Length , 1999, IEEE Trans. Inf. Theory.