Sparse and Low-Rank Tensor Estimation via Cubic Sketchings

DOI10.1109/TIT.2020.2982499MaRDI QIDQ5124548zbMATH OpenOpenAlexFDO

Authors Botao Hao, Anru Zhang, Guang Cheng

Publication date 29 September 2020

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1801.09326

Mathematics Subject Classification ID

Multilinear algebra, tensor calculus (15A69) Estimation in multivariate analysis (62H12) Numerical methods for low-rank matrix approximation; matrix compression (65F55) Nonconvex programming, global optimization (90C26)

Abstract: In this paper, we propose a general framework for sparse and low-rank tensor estimation from cubic sketchings. A two-stage non-convex implementation is developed based on sparse tensor decomposition and thresholded gradient descent, which ensures exact recovery in the noiseless case and stable recovery in the noisy case with high probability. The non-asymptotic analysis sheds light on an interplay between optimization error and statistical error. The proposed procedure is shown to be rate-optimal under certain conditions. As a technical by-product, novel high-order concentration inequalities are derived for studying high-moment sub-Gaussian tensors. An interesting tensor formulation illustrates the potential application to high-order interaction pursuit in high-dimensional linear regression.

Cited in

(24)

• Subspace estimation from unbalanced and incomplete data matrices: \({\ell_{2,\infty}}\) statistical guarantees
• Sparse random tensors: concentration, regularization and applications
• An optimal statistical and computational framework for generalized tensor estimation
• Inference for low-rank tensors -- no need to debias
• Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval
• Tensor sparsification via a bound on the spectral norm of random tensors: Algorithm 1.
• Sparse tensor additive regression
• ISLET: fast and optimal low-rank tensor regression via importance sketching
• Tensor Regression Using Low-Rank and Sparse Tucker Decompositions
• Nonconvex Low-Rank Tensor Completion from Noisy Data
• Generalized Tensor Decomposition With Features on Multiple Modes
• A sharp blockwise tensor perturbation bound for orthogonal iteration
• Robust Recovery of Low-Rank Matrices and Low-Tubal-Rank Tensors from Noisy Sketches
• Generalized Liquid Association Analysis for Multimodal Data Integration
• Partially Observed Dynamic Tensor Response Regression
• Generalized Low-Rank Plus Sparse Tensor Estimation by Fast Riemannian Optimization
• Covariate-Assisted Sparse Tensor Completion
• Optimality conditions for Tucker low-rank tensor optimization
• An improved tensor regression model via location smoothing
• Low-rank tensor regression for selection of grouped variables
• CP factor model for dynamic tensors
• A fast correction approach to tensor robust principal component analysis
• Tensor-on-tensor regression: Riemannian optimization, over-parameterization, statistical-computational gap and their interplay
• Statistical inference for low-rank tensors: heteroskedasticity, subgaussianity, and applications

This page was built for publication: Sparse and Low-Rank Tensor Estimation via Cubic Sketchings

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5124548)