Minimax estimation of linear functionals over nonconvex parameter spaces

Abstract

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.

Cited by in corpus (11)

• Testing composite hypotheses, Hermite polynomials and optimal estimation of a nonsmooth functional
• An adaptation theory for nonparametric confidence intervals
• Minimax estimation of linear and quadratic functionals on sparsity classes
• Nonquadratic estimators of a quadratic functional
• On deconvolution of distribution functions
• On the minimax optimality and superiority of deep neural network learning over sparse parameter spaces
• Minimax and Adaptive Inference in Nonparametric Function Estimation
• Geometric Inference for General High-Dimensional Linear Inverse Problems
• On adaptive estimation of linear functionals
• Adaptive estimation of linear functionals by model selection
• Near-Optimal Recovery of Linear and N-Convex Functions on Unions of Convex Sets