Sparse CCA: adaptive estimation and computational barriers
This paper considers adaptive minimax and computationally tractable estimation of leading sparse canonical coefficient vectors in high dimensions. Assume that \(X\in\mathbb{R}^p\) and \(Y\in\mathbb{R}^m\) are random vectors. Let the linear combinations \((u_j'X, v_j'Y)\) be the \(j\)th pair of canonical variates. Suppose that there are \(r\) pairs of canonical coefficient vectors (and canonical variates) among the two sets of variables. Denote \({U}=[{u}_1,\dots,{u}_r]\) and \({V}=[{v}_1,\dots,v_r]\). Instead of considering the joint loss \(\|\hat{{U}}\hat{{V}}'-{{U}}{{V}}\|\) of the estimation \(\hat{{U}}\) and \(\hat{{V}}\) of \(U\) and \(V\), this paper provides a finer analysis by studying individual estimation errors of \(U\) and \(V\) under a natural loss function that can be interpreted as prediction error of canonical variates. Under a Gaussian canonical pair model, it first establishes separate minimax estimation rates for canonical coefficient vectors of each set of random variables under no structural assumption on marginal covariance matrices. Second, it proposes a computationally feasible estimator to attain the optimal rates adaptively under an additional sample size condition. Finally, it shows that a sample size condition of this kind is needed for any randomized polynomial-time estimator to be consistent, assuming hardness of certain instances of the planted clique detection problem. As a byproduct, the first computational lower bounds is obtained for sparse PCA under the Gaussian single spiked covariance model.
- Minimax estimation in sparse canonical correlation analysis
- Statistical and computational trade-offs in estimation of sparse principal components
- Sparse CCA via precision adjusted iterative thresholding
- Minimax sparse principal subspace estimation in high dimensions
- Sparse PCA: optimal rates and adaptive estimation
- Canonical correlation coefficients of high-dimensional Gaussian vectors: finite rank case
- Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics
- Optimal estimation of slope vector in high-dimensional linear transformation models
- Semiparametric efficiency bounds for high-dimensional models
- Minimax rates in network analysis: graphon estimation, community detection and hypothesis testing
- Eigenvector-based sparse canonical correlation analysis: fast computation for estimation of multiple canonical vectors
- Advanced topics in sliced inverse regression
- The overlap gap property in principal submatrix recovery
- A sieve stochastic gradient descent estimator for online nonparametric regression in Sobolev ellipsoids
- Tensor clustering with planted structures: statistical optimality and computational limits
- Computational barriers to estimation from low-degree polynomials
- Sparse SIR: optimal rates and adaptive estimation
- tSSNALM: a fast two-stage semi-smooth Newton augmented Lagrangian method for sparse CCA
- Sparse generalized canonical correlation analysis via linearized Bregman method
- Statistical and computational limits for sparse matrix detection
- Estimation of canonical correlation directions: from Gaussian to sub-Gaussian population
- Subspace perspective on canonical correlation analysis: dimension reduction and minimax rates
- Sparse PCA: optimal rates and adaptive estimation
- Optimal estimation for lower bound of the packing number
- Integrative analysis of transcriptomic and metabolomic data via sparse canonical correlation analysis with incorporation of biological information
- D-CCA: A Decomposition-Based Canonical Correlation Analysis for High-Dimensional Datasets
- Penalized Orthogonal Iteration for Sparse Estimation of Generalized Eigenvalue Problem
- Eigenvectors from Eigenvalues Sparse Principal Component Analysis
- Finding a planted clique by adaptive probing
- scientific article; zbMATH DE number 7164767 (Why is no real title available?)
- Sparse CCA via precision adjusted iterative thresholding
- Computationally efficient sparse clustering
- Estimating structured high-dimensional covariance and precision matrices: optimal rates and adaptive estimation
- Rejoinder of ``Estimating structured high-dimensional covariance and precision matrices: optimal rates and adaptive estimation
- Joint association and classification analysis of multi‐view data
- Sample canonical correlation coefficients of high-dimensional random vectors: Local law and Tracy–Widom limit
- An Efficient Convex Formulation for Reduced-Rank Linear Discriminant Analysis in High Dimensions
- Sample canonical correlation coefficients of high-dimensional random vectors with finite rank correlations
- A penalty-free infeasible approach for a class of nonsmooth optimization problems over the Stiefel manifold
- Estimation of misclassification rate in the Asymptotic Rare and Weak model with sub-Gaussian noises
- Hardness self-amplification: simplified, optimized, and unified
- High-dimensional sparse single-index regression via Hilbert-Schmidt independence criterion
- Trace Lasso regularization for adaptive sparse canonical correlation analysis via manifold optimization approach
- Minimax Quasi-Bayesian Estimation in Sparse Canonical Correlation Analysis via a Rayleigh Quotient Function
- Computational lower bounds for graphon estimation via low-degree polynomials
- Asymmetric canonical correlation analysis of Riemannian and high-dimensional data
- Efficient computation of sparse and robust maximum association estimators
- Federated sufficient dimension reduction through high-dimensional sparse sliced inverse regression
- Optimal estimation of misclassification rate for two-class clustering with sub-Gaussian noises
- Estimation of leading multi-block canonical correlation directions via _1-norm constrained proximal gradient descent
- Tensor factor model estimation by iterative projection
- The strongish planted clique hypothesis and its consequences
- Three equivalent distances about singular subspaces
- Sparse higher-order partial least squares for simultaneous variable selection, dimension reduction and tensor denoising
- Optimal Sparse Sliced Inverse Regression via Random Projection
- Efficient canonical correlation analysis with sparsity
- Differentially private upper bounds for covariance and inverse covariance matrices
- Minimax estimation in sparse canonical correlation analysis
This page was built for publication: Sparse CCA: adaptive estimation and computational barriers
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1687119)
