论文信息 - Minimax estimation of linear functionals over nonconvex parameter spaces

Minimax estimation of linear functionals over nonconvex parameter spaces

The minimax theory for estimating linear functionals is extended to the case of a finite union of convex parameter spaces. Upper and lower bounds for the minimax risk can still be described in terms of a modulus of continuity. However in contrast to the theory for convex parameter spaces rate optimal procedures are often required to be nonlinear. A construction of such nonlinear procedures is given. The results developed in this paper have important applications to the theory of adaptation.

T. Cai | Mark G. Low

[1] William Feller,et al. An Introduction to Probability Theory and Its Applications , 1951 .

[2] P. A. P. Moran,et al. An introduction to probability theory , 1968 .

[3] I. Ibragimov,et al. On Nonparametric Estimation of the Value of a Linear Functional in Gaussian White Noise , 1985 .

[4] D. Donoho,et al. Geometrizing Rates of Convergence, III , 1991 .

[5] O. Lepskii. On a Problem of Adaptive Estimation in Gaussian White Noise , 1991 .

[6] I. Johnstone,et al. Maximum Entropy and the Nearly Black Object , 1992 .

[7] Sam Efromovich,et al. Adaptive estimates of linear functionals , 1994 .

[8] D. Donoho. Statistical Estimation and Optimal Recovery , 1994 .

[9] Mark G. Low. Bias-Variance Tradeoffs in Functional Estimation Problems , 1995 .

[10] I. Johnstone,et al. Wavelet Shrinkage: Asymptopia? , 1995 .

[11] L. Brown,et al. A constrained risk inequality with applications to nonparametric functional estimation , 1996 .

[12] On Modulus of Continuity And Adaptability in Nonparametric Functional Estimation , 2002 .

[13] Y. Baraud. Non-asymptotic minimax rates of testing in signal detection , 2002 .

[14] I. Johnstone,et al. Adapting to unknown sparsity by controlling the false discovery rate , 2005, math/0505374.