Adaptive Threshold Estimation by FDR

This paper addresses the following simple question about sparsity. For the estimation of an $n$-dimensional mean vector $\boldsymbol{\theta}$ in the Gaussian sequence model, is it possible to find an adaptive optimal threshold estimator in a full range of sparsity levels where nonadaptive optimality can be achieved by threshold estimators? We provide an explicit affirmative answer as follows. Under the squared loss, adaptive minimaxity in strong and weak $\ell_p$ balls with $0\le p<2$ is achieved by a class of smooth threshold estimators with the threshold level of the Benjamini-Hochberg FDR rule or its a certain approximation, provided that the minimax risk is between $n^{-\delta_n}$ and $\delta_n n$ for some $\delta_n\to 0$. For $p=0$, this means adaptive minimaxity in $\ell_0$ balls when $1\le \|\boldsymbol{\theta}\|_0\ll n$. The class of smooth threshold estimators includes the soft and firm threshold estimators but not the hard threshold estimator. The adaptive minimaxity in such a wide range is a delicate problem since the same is not true for the FDR hard threshold estimator at certain threshold and nominal FDR levels. The above adaptive minimaxity of the FDR smooth-threshold estimator is established by proving a stronger notion of adaptive ratio optimality for the soft threshold estimator in the sense that the risk for the FDR threshold level is uniformly within an infinitesimal fraction of the risk for the optimal threshold level for each unknown vector, when the minimum risk of nonadaptive soft threshold estimator is between $n^{-\delta_n}$ and $\delta_n n$. It is an interesting consequence of this adaptive ratio optimality that the FDR smooth-threshold estimator outperforms the sample mean in the common mean model $\theta_i=\mu$ when $|\mu|

[1]  R. Tibshirani,et al.  The Covariance Inflation Criterion for Adaptive Model Selection , 1999 .

[2]  H. Robbins Asymptotically Subminimax Solutions of Compound Statistical Decision Problems , 1985 .

[3]  Cun-Hui Zhang Minimax ℓq risk in ℓp balls , 2012 .

[4]  Harrison H. Zhou,et al.  Model selection and sharp asymptotic minimaxity , 2013 .

[5]  H. Robbins An Empirical Bayes Approach to Statistics , 1956 .

[6]  D. L. Donoho,et al.  Ideal spacial adaptation via wavelet shrinkage , 1994 .

[7]  B. Efron,et al.  Empirical Bayes on vector observations: An extension of Stein's method , 1972 .

[8]  I. Johnstone,et al.  Adapting to Unknown Smoothness via Wavelet Shrinkage , 1995 .

[9]  S. Holm A Simple Sequentially Rejective Multiple Test Procedure , 1979 .

[10]  Lawrence D. Brown,et al.  NONPARAMETRIC EMPIRICAL BAYES AND COMPOUND DECISION APPROACHES TO ESTIMATION OF A HIGH-DIMENSIONAL VECTOR OF NORMAL MEANS , 2009, 0908.1712.

[11]  I. Johnstone,et al.  Minimax Risk over l p-Balls for l q-error , 1994 .

[12]  Wenhua Jiang,et al.  General maximum likelihood empirical Bayes estimation of normal means , 2009, 0908.1709.

[13]  Yuhong Yang,et al.  An Asymptotic Property of Model Selection Criteria , 1998, IEEE Trans. Inf. Theory.

[14]  I. Johnstone Minimax Bayes, Asymptotic Minimax and Sparse Wavelet Priors , 1994 .

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

[16]  I. Johnstone,et al.  Needles and straw in haystacks: Empirical Bayes estimates of possibly sparse sequences , 2004, math/0410088.

[17]  B. Efron,et al.  Stein's Estimation Rule and Its Competitors- An Empirical Bayes Approach , 1973 .

[18]  A. Bruce,et al.  WAVESHRINK WITH FIRM SHRINKAGE , 1997 .

[19]  P. Massart,et al.  Gaussian model selection , 2001 .

[20]  Cun-Hui Zhang,et al.  Compound decision theory and empirical bayes methods , 2003 .

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

[22]  Cun-Hui Zhang General empirical Bayes wavelet methods and exactly adaptive minimax estimation , 2005, math/0504501.

[23]  Y. Benjamini,et al.  Controlling the false discovery rate: a practical and powerful approach to multiple testing , 1995 .

[24]  Cun-Hui Zhang Nearly unbiased variable selection under minimax concave penalty , 2010, 1002.4734.

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

[26]  C. Borell The Brunn-Minkowski inequality in Gauss space , 1975 .

[27]  C. Morris Parametric Empirical Bayes Inference: Theory and Applications , 1983 .

[28]  Cun-Hui Zhang,et al.  EMPIRICAL BAYES AND COMPOUND ESTIMATION OF NORMAL MEANS , 1997 .

[29]  Jianqing Fan,et al.  Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties , 2001 .

[30]  H. Robbins Some Thoughts on Empirical Bayes Estimation , 1983 .

[31]  P. Massart,et al.  Concentration inequalities and model selection , 2007 .

[32]  J. Neyman,et al.  INADMISSIBILITY OF THE USUAL ESTIMATOR FOR THE MEAN OF A MULTIVARIATE NORMAL DISTRIBUTION , 2005 .

[33]  P. Gänssler Weak Convergence and Empirical Processes - A. W. van der Vaart; J. A. Wellner. , 1997 .

[34]  C. Stein,et al.  Estimation with Quadratic Loss , 1992 .

[35]  Dean Phillips Foster,et al.  Calibration and Empirical Bayes Variable Selection , 1997 .