Efficient estimation of linear functionals of principal components
From MaRDI portal
Abstract: We study principal component analysis (PCA) for mean zero i.i.d. Gaussian observations in a separable Hilbert space with unknown covariance operator The complexity of the problem is characterized by its effective rank where denotes the trace of and denotes its operator norm. We develop a method of bias reduction in the problem of estimation of linear functionals of eigenvectors of Under the assumption that we establish the asymptotic normality and asymptotic properties of the risk of the resulting estimators and prove matching minimax lower bounds, showing their semi-parametric optimality.
In the setting of principal component analysis for \(n\) IID, mean zero Gaussian observations in a separable Hilbert space, the authors consider the estimation problem for linear functionals of eigenvalues of the unknown covariance operator \(\Sigma\). The effective rank \(r(\Sigma)=\mbox{tr}(\Sigma)/\|\Sigma\|\) is used to quantify the complexity of the problem, where \(\mbox{tr}(\Sigma)\) is the trace of \(\Sigma\) and \(\|\Sigma\|\) is its operator norm. No assumptions on the structure of \(\Sigma\) are made, though eigenvalues to be estimated are assumed to be simple (i.e., have multiplicity 1). It is known that naive estimators can suffer from substantial bias when this effective rank is large with respect to \(n\). For the case where \(r(\Sigma)=o(n)\), the authors propose a bias reduction technique and show asymptotic normality of their estimator. Their upper bounds are complemented by lower bounds that demonstrate semiparametric optimality of their estimator in this case.
Recommendations
Cites work
- A general theory of hypothesis tests and confidence regions for sparse high dimensional models
- Applications of the van Trees inequality: A Bayesian Cramér-Rao bound
- Asymptotic normality and optimalities in estimation of large Gaussian graphical models
- Asymptotic Statistics
- Asymptotic Theory for Principal Component Analysis
- Asymptotic theory for the principal component analysis of a vector random function: Some applications to statistical inference
- Asymptotically efficient estimation of smooth functionals of covariance operators
- Asymptotics and concentration bounds for bilinear forms of spectral projectors of sample covariance
- Asymptotics of empirical eigenstructure for high dimensional spiked covariance
- Asymptotics of sample eigenstructure for a large dimensional spiked covariance model
- Bernstein-von Mises theorems for functionals of the covariance matrix
- Concentration inequalities and moment bounds for sample covariance operators
- Confidence Intervals and Hypothesis Testing for High-Dimensional Regression
- Confidence intervals for high-dimensional linear regression: minimax rates and adaptivity
- Confidence intervals for low dimensional parameters in high dimensional linear models
- Confidence sets for spectral projectors of covariance matrices
- Efficient estimation of linear functionals of principal components
- Estimation of functionals of sparse covariance matrices
- Finite sample approximation results for principal component analysis: A matrix perturbation approach
- Functional data analysis.
- scientific article; zbMATH DE number 3942782 (Why is no real title available?)
- Learning Theory
- Mathematical foundations of infinite-dimensional statistical models
- Minimax sparse principal subspace estimation in high dimensions
- New asymptotic results in principal component analysis
- Nonasymptotic upper bounds for the reconstruction error of PCA
- Normal approximation and concentration of spectral projectors of sample covariance
- On asymptotically optimal confidence regions and tests for high-dimensional models
- On the distribution of the largest eigenvalue in principal components analysis
- On the principal components of sample covariance matrices
- Optimal detection of sparse principal components in high dimension
- Rate-optimal posterior contraction for sparse PCA
- Semiparametric efficiency bounds for high-dimensional models
- Smooth principal component analysis over two-dimensional manifolds with an application to neuroimaging
- Sparse PCA: optimal rates and adaptive estimation
- Statistical and computational trade-offs in estimation of sparse principal components
- The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices
- Weak convergence and empirical processes. With applications to statistics
Cited in
(36)- New asymptotic results in principal component analysis
- On the asymptotic normality and efficiency of Kronecker envelope principal component analysis
- Efficient estimation of smooth functionals in Gaussian shift models
- Estimation of smooth functionals of location parameter in Gaussian and Poincaré random shift models.
- Estimation of smooth functionals in normal models: bias reduction and asymptotic efficiency
- Estimation of smooth functionals in high-dimensional models: bootstrap chains and Gaussian approximation
- Bootstrapping the operator norm in high dimensions: error estimation for covariance matrices and sketching
- Lower bounds for invariant statistical models with applications to principal component analysis
- Efficient estimation of linear functionals of principal components
- Bootstrapping max statistics in high dimensions: near-parametric rates under weak variance decay and application to functional and multinomial data
- Estimating covariance and precision matrices along subspaces
- Convergence rate of Krasulina estimator
- On the sample covariance matrix estimator of reduced effective rank population matrices, with applications to fPCA
- Singular vector and singular subspace distribution for the matrix denoising model
- Asymptotically efficient estimation of smooth functionals of covariance operators
- PCA-kernel estimation
- Efficient Multidimensional Diracs Estimation With Linear Sample Complexity
- scientific article; zbMATH DE number 5252 (Why is no real title available?)
- scientific article; zbMATH DE number 1822207 (Why is no real title available?)
- Asymptotic efficiency in high-dimensional covariance estimation
- Wald Statistics in high-dimensional PCA
- Rates of Bootstrap Approximation for Eigenvalues in High-Dimensional PCA
- Distribution function estimation with calibration on principal components
- Inference for low-rank models
- Inference for heteroskedastic PCA with missing data
- Quantitative limit theorems and bootstrap approximations for empirical spectral projectors
- Estimation and inference for CP tensor factor models
- Sharp concentration of simple random tensors
- Mode-wise principal subspace pursuit and matrix spiked covariance model
- Concentration and consistency of sample covariance matrix functionals in sub-Gaussian models
- On the multiway principal component analysis
- Large-dimensional independent component analysis: statistical optimality and computational tractability
- Estimation of smooth functionals of covariance operators: jackknife bias reduction and bounds in terms of effective rank
- Inference for Low-Rank Models Without Estimating the Rank
- Sampled forms of functional PCA in reproducing kernel Hilbert spaces
- Principal components in linear mixed models with general bulk
This page was built for publication: Efficient estimation of linear functionals of principal components
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2176629)
