Lower bounds for invariant statistical models with applications to principal component analysis

DOI10.1214/21-AIHP1193zbMATH Open1493.62025arXiv2005.06869OpenAlexW3186499112MaRDI QIDQ2157446FDOQ2157446

Authors: Martin Wahl 

Publication date: 22 July 2022

Published in: Annales de l'Institut Henri Poincaré. Probabilités et Statistiques (Search for Journal in Brave)

Abstract: This paper develops nonasymptotic information inequalities for the estimation of the eigenspaces of a covariance operator. These results generalize previous lower bounds for the spiked covariance model, and they show that recent upper bounds for models with decaying eigenvalues are sharp. The proof relies on lower bound techniques based on group invariance arguments which can also deal with a variety of other statistical models.

Full work available at URL: https://arxiv.org/abs/2005.06869

Recommendations

• The statistics and mathematics of high dimension low sample size asymptotics
• Minimax sparse principal subspace estimation in high dimensions
• Efficient estimation of linear functionals of principal components
• Minimax bounds for sparse PCA with noisy high-dimensional data
• High-dimensional principal projections

zbMATH Keywords

principal componentslarge deviationslower boundsFisher informationcovariance operatorspecial orthogonal groupequivariant modelVan Trees inequality

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Factor analysis and principal components; correspondence analysis (62H25)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Support Vector Machines
• Title not available (Why is that?)
• Asymptotic Statistics
• Real Analysis and Probability
• Theoretical Foundations of Functional Data Analysis, with an Introduction to Linear Operators
• Asymptotics of sample eigenstructure for a large dimensional spiked covariance model
• Asymptotic theory for the principal component analysis of a vector random function: Some applications to statistical inference
• Finite sample approximation results for principal component analysis: A matrix perturbation approach
• Mathematical theory of statistics. Statistical experiments and asymptotic decision theory
• Title not available (Why is that?)
• Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics
• Estimation of a covariance matrix using the reference prior
• Sparse PCA: optimal rates and adaptive estimation
• An introduction to random matrices
• Title not available (Why is that?)
• Large deviations techniques and applications.
• Applications of the van Trees inequality: A Bayesian Cramér-Rao bound
• Stochastic Equations in Infinite Dimensions
• Title not available (Why is that?)
• High-dimensional principal projections
• Title not available (Why is that?)
• Introduction to nonparametric estimation
• Methodology and convergence rates for functional linear regression
• Title not available (Why is that?)
• Title not available (Why is that?)
• A new concentration result for regularized risk minimizers
• Minimax sparse principal subspace estimation in high dimensions
• Title not available (Why is that?)
• A large deviation theorem for the empirical eigenvalue distribution of random unitary matrices
• Title not available (Why is that?)
• Multivariate calculation. Use of the continuous groups
• Optimal estimation and rank detection for sparse spiked covariance matrices
• Large deviations for functions of two random projection matrices
• Optimal rates for regularization of statistical inverse learning problems
• Optimality and sub-optimality of PCA. I: Spiked random matrix models
• Information Geometry
• The Random Matrix Theory of the Classical Compact Groups
• A van Trees inequality for estimators on manifolds
• Nonasymptotic upper bounds for the reconstruction error of PCA
• Random perturbation of low rank matrices: improving classical bounds
• Message‐Passing Algorithms for Synchronization Problems over Compact Groups
• Asymptotically efficient estimation of smooth functionals of covariance operators
• Efficient estimation of linear functionals of principal components
• Perturbation bounds for eigenspaces under a relative gap condition
• Mathematics, Models, and Magz, Part I: Patterns in Pascal's Triangle and Tetrahedron
• Title not available (Why is that?)
• Exact Minimax Estimation for Phase Synchronization

Cited In (5)

• On lower bounds for the bias-variance trade-off
• Functional estimation in log-concave location families
• Transposition invariant principal component analysis in \(L_{1}\) for long tailed data
• Re-thinking high-dimensional mathematical statistics. Abstracts from the workshop held May 15--21, 2022
• Van Trees inequality, group equivariance, and estimation of principal subspaces

This page was built for publication: Lower bounds for invariant statistical models with applications to principal component analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2157446)