Efficient Estimation of Smooth Functionals in Gaussian Shift Models

by   Vladimir Koltchinskii, et al.

We study a problem of estimation of smooth functionals of parameter θ of Gaussian shift model X=θ +ξ, θ∈ E, where E is a separable Banach space and X is an observation of unknown vector θ in Gaussian noise ξ with zero mean and known covariance operator Σ. In particular, we develop estimators T(X) of f(θ) for functionals f:E R of Hölder smoothness s>0 such that _θ≤ 1 E_θ(T(X)-f(θ))^2 ≲(Σ∨ ( Eξ^2)^s)∧ 1, where Σ is the operator norm of Σ, and show that this mean squared error rate is minimax optimal (up to a logarithmic factor) at least in the case of standard Gaussian shift model (E= R^d equipped with the canonical Euclidean norm, ξ =σ Z, Z∼ N(0;I_d)). Moreover, we determine a sharp threshold on the smoothness s of functional f such that, for all s above the threshold, f(θ) can be estimated efficiently with a mean squared error rate of the order Σ in a "small noise" setting (that is, when Eξ^2 is small). The construction of efficient estimators is crucially based on a "bootstrap chain" method of bias reduction. The results could be applied to a variety of special high-dimensional and infinite-dimensional Gaussian models (for vector, matrix and functional data).


page 1

page 2

page 3

page 4


Estimation of smooth functionals of covariance operators: jackknife bias reduction and bounds in terms of effective rank

Let E be a separable Banach space and let X, X_1,…, X_n, … be i.i.d. Gau...

A Fourier Analytical Approach to Estimation of Smooth Functions in Gaussian Shift Model

We study the estimation of f() under Gaussian shift model = +, where ∈^d...

Rate-optimal estimation of p-dimensional linear functionals in a sparse Gaussian model

We consider two problems of estimation in high-dimensional Gaussian mode...

Estimation of Bandlimited Grayscale Images From the Single Bit Observations of Pixels Affected by Additive Gaussian Noise

The estimation of grayscale images using their single-bit zero mean Gaus...

Stretching the Effectiveness of MLE from Accuracy to Bias for Pairwise Comparisons

A number of applications (e.g., AI bot tournaments, sports, peer grading...

Wide flat minima and optimal generalization in classifying high-dimensional Gaussian mixtures

We analyze the connection between minimizers with good generalizing prop...

Functional estimation in log-concave location families

Let {P_θ:θ∈ℝ^d} be a log-concave location family with P_θ(dx)=e^-V(x-θ)d...

Please sign up or login with your details

Forgot password? Click here to reset