DeepAI AI Chat
Log In Sign Up

Information inequalities for the estimation of principal components

by   Martin Wahl, et al.
Humboldt-Universität zu Berlin

We provide lower bounds for the estimation of the eigenspaces of a covariance operator. These information inequalities are non-asymptotic and can be applied to any sequence of eigenvalues. In the important case of the eigenspace of the d leading eigenvalues, the lower bounds match non-asymptotic upper bounds based on the empirical covariance operator. Our approach relies on a van Trees inequality for equivariant models, with the reference measure being the Haar measure on the orthogonal group, combined with large deviations techniques to design optimal prior densities.


page 1

page 2

page 3

page 4


Non asymptotic estimation lower bounds for LTI state space models with Cramér-Rao and van Trees

We study the estimation problem for linear time-invariant (LTI) state-sp...

Van Trees inequality, group equivariance, and estimation of principal subspaces

We establish non-asymptotic lower bounds for the estimation of principal...

Computational lower bounds of the Maxwell eigenvalues

A method to compute guaranteed lower bounds to the eigenvalues of the Ma...

First order covariance inequalities via Stein's method

We propose probabilistic representations for inverse Stein operators (i....

Towards a Complete Analysis of Langevin Monte Carlo: Beyond Poincaré Inequality

Langevin diffusions are rapidly convergent under appropriate functional ...

Asymptotic efficiency for covariance estimation under noise and asynchronicity

The estimation of the covariance structure from a discretely observed mu...

The Best Bounds for Range Type Statistics

In this paper, we obtain the upper and lower bounds for two inequalities...