Sparse PCA: Optimal rates and adaptive estimation
Reads0
Chats0
TLDR
In this paper, the authors considered both minimax and adaptive estimation of the principal subspace in the high dimensional setting and established the optimal rates of convergence for estimating the subspace which are sharp with respect to all the parameters, thus providing a complete characterization of the difficulty of the estimation problem in terms of the convergence rate.Abstract:
Principal component analysis (PCA) is one of the most commonly used statistical procedures with a wide range of applications. This paper considers both minimax and adaptive estimation of the principal subspace in the high dimensional setting. Under mild technical conditions, we first establish the optimal rates of convergence for estimating the principal subspace which are sharp with respect to all the parameters, thus providing a complete characterization of the difficulty of the estimation problem in term of the convergence rate. The lower bound is obtained by calculating the local metric entropy and an application of Fano’s lemma. The rate optimal estimator is constructed using aggregation, which, however, might not be computationally feasible. We then introduce an adaptive procedure for estimating the principal subspace which is fully data driven and can be computed efficiently. It is shown that the estimator attains the optimal rates of convergence simultaneously over a large collection of the parameter spaces. A key idea in our construction is a reduction scheme which reduces the sparse PCA problem to a high-dimensional multivariate regression problem. This method is potentially also useful for other related problems.read more
Citations
More filters
Journal ArticleDOI
Do semidefinite relaxations solve sparse pca up to the information limit
TL;DR: For a single-spike model with an ε-sparse eigenvector, in the asymptotic regime as dimension $p$ and sample size $n$ both tend to infinity.
Journal ArticleDOI
Minimax estimation in sparse canonical correlation analysis
TL;DR: In this article, the authors considered the problem of estimating the leading canonical correlation directions in high-dimensional settings and established rate-optimal nonasymptotic minimax estimation with respect to an appropriate loss function for a wide range of model spaces.
Journal ArticleDOI
Sparse Principal Component Analysis via Variable Projection
N. Benjamin Erichson,Peng Zheng,Krithika Manohar,Steven L. Brunton,J. Nathan Kutz,Aleksandr Y. Aravkin +5 more
TL;DR: In this article, a robust and scalable sparse principal component analysis (SPCA) algorithm was proposed by formulating it as a value function optimization problem, which leads to a flexible and computationally efficient algorithm.
Posted Content
Symmetry, Saddle Points, and Global Optimization Landscape of Nonconvex Matrix Factorization
TL;DR: The proposed general theory for studying the geometry of nonconvex objective functions with underlying symmetric structures describes how the rotational symmetry group gives rise to infinitely many nonisolated strict saddle points and equivalent global minima of the objective function.
Journal ArticleDOI
Optimal Sparse Singular Value Decomposition for High-Dimensional High-Order Data
Anru Zhang,Rungang Han +1 more
TL;DR: In this article, the sparse tensor singular value decomposition (SSTV decomposition) is used for dimension reduction on high-dimensional high-order data with sparsity structure.
References
More filters
Book
Elements of information theory
Thomas M. Cover,Joy A. Thomas +1 more
TL;DR: The author examines the role of entropy, inequality, and randomness in the design of codes and the construction of codes in the rapidly changing environment.
Book
Matrix Analysis
Roger A. Horn,Charles R. Johnson +1 more
TL;DR: In this article, the authors present results of both classic and recent matrix analyses using canonical forms as a unifying theme, and demonstrate their importance in a variety of applications, such as linear algebra and matrix theory.
Book
An Introduction to Multivariate Statistical Analysis
TL;DR: In this article, the distribution of the Mean Vector and the Covariance Matrix and the Generalized T2-Statistic is analyzed. But the distribution is not shown to be independent of sets of Variates.
Journal ArticleDOI
Introduction to Multivariate Statistical Analysis.
William G. Madow,T. W. Anderson +1 more
Journal ArticleDOI
Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
TL;DR: It is shown that if a certain restricted isometry property holds for the linear transformation defining the constraints, the minimum-rank solution can be recovered by solving a convex optimization problem, namely, the minimization of the nuclear norm over the given affine space.