Optimal sparse singular value decomposition for high-dimensional high-order data
From MaRDI portal
Abstract: In this article, we consider the sparse tensor singular value decomposition, which aims for dimension reduction on high-dimensional high-order data with certain sparsity structure. A method named Sparse Tensor Alternating Thresholding for Singular Value Decomposition (STAT-SVD) is proposed. The proposed procedure features a novel double projection & thresholding scheme, which provides a sharp criterion for thresholding in each iteration. Compared with regular tensor SVD model, STAT-SVD permits more robust estimation under weaker assumptions. Both the upper and lower bounds for estimation accuracy are developed. The proposed procedure is shown to be minimax rate-optimal in a general class of situations. Simulation studies show that STAT-SVD performs well under a variety of configurations. We also illustrate the merits of the proposed procedure on a longitudinal tensor dataset on European country mortality rates.
Recommendations
Cites work
- A Multilinear Singular Value Decomposition
- An alternative point of view on Lepski's method
- Biclustering via sparse singular value decomposition
- Dynamic tensor clustering
- Generalized L-, M-, and R-statistics
- Influential features PCA for high dimensional clustering
- Most tensor problems are NP-hard
- On consistency and sparsity for principal components analysis in high dimensions
- On the Best Rank-1 and Rank-(R1 ,R2 ,. . .,RN) Approximation of Higher-Order Tensors
- Optimal estimation of low rank density matrices
- Principal component analysis.
- Provable sparse tensor decomposition
- Rate Optimal Denoising of Simultaneously Sparse and Low Rank Matrices
- Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics
- Selecting the number of principal components: estimation of the true rank of a noisy matrix
- Sparse PCA: optimal rates and adaptive estimation
- Sparse principal component analysis via regularized low rank matrix approximation
- Tensor Decompositions and Applications
- Tensor decompositions for learning latent variable models
- Tensor Rank and the Ill-Posedness of the Best Low-Rank Approximation Problem
Cited in
(37)- High order singular value decomposition for plant diversity estimation
- Community detection on mixture multilayer networks via regularized tensor decomposition
- Tucker-3 decomposition with sparse core array using a penalty function based on Gini-index
- An optimal statistical and computational framework for generalized tensor estimation
- Tensor clustering with planted structures: statistical optimality and computational limits
- Inference for low-rank tensors -- no need to debias
- A general framework for tensor screening through smoothing
- Several approximation algorithms for sparse best rank-1 approximation to higher-order tensors
- Adaptive higher-order spectral estimators
- scientific article; zbMATH DE number 663830 (Why is no real title available?)
- Sparse tensor additive regression
- ISLET: fast and optimal low-rank tensor regression via importance sketching
- Adaptive singular value shrinkage estimate for low rank tensor denoising
- A sharp blockwise tensor perturbation bound for orthogonal iteration
- Statistical inference on the significance of rows and columns for matrix-valued data in an additive model
- Generalized Liquid Association Analysis for Multimodal Data Integration
- Correlation Tensor Decomposition and Its Application in Spatial Imaging Data
- Multivariate Temporal Point Process Regression
- A Doubly Enhanced EM Algorithm for Model-Based Tensor Clustering
- Covariate-Assisted Sparse Tensor Completion
- Model-Based Tensor Low-Rank Clustering
- Guaranteed Functional Tensor Singular Value Decomposition
- Smoothing composite proximal gradient algorithm for sparse group Lasso problems with nonsmooth loss functions
- Multilayer random dot product graphs: estimation and online change point detection
- Tucker tensor factor models: matricization and mode-wise PCA estimation
- Sharp concentration of simple random tensors
- Dimension selection in tensor decompositions and envelope models
- Distributed Tensor Principal Component Analysis with Data Heterogeneity
- Fourth order random tensors and their applications in statistics
- Tensor factor adjustment for image classification with pervasive noises
- On minimal smallest singular value of subframes for signal recovery
- The Tucker low-rank classification model for tensor data
- Sparse higher-order partial least squares for simultaneous variable selection, dimension reduction and tensor denoising
- Sharp optimality of sparse group LASSO and SLOPE under weaker assumptions
- Statistical inference for low-rank tensors: heteroskedasticity, subgaussianity, and applications
- Sharp concentration of simple random tensors. II: Asymmetry
- Multivariate Analysis for Multiple Network Data via Semi-Symmetric Tensor PCA
This page was built for publication: Optimal sparse singular value decomposition for high-dimensional high-order data
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5208075)
