Statistically optimal and computationally efficient low rank tensor completion from noisy entries

DOI10.1214/20-AOS1942zbMath1473.62184arXiv1711.04934OpenAlexW3127320487MaRDI QIDQ2656588

Dong Xia, Cun-Hui Zhang, Ming Yuan

Publication date: 11 March 2021

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1711.04934

zbMATH Keywords

minimax optimalitypower iterationspectral initialization

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Computational methods for problems pertaining to statistics (62-08) Estimation in multivariate analysis (62H12)

Related Items (14)

An optimal statistical and computational framework for generalized tensor estimation ⋮ Partially Observed Dynamic Tensor Response Regression ⋮ Generalized Low-Rank Plus Sparse Tensor Estimation by Fast Riemannian Optimization ⋮ Covariate-Assisted Sparse Tensor Completion ⋮ Optimal estimation and computational limit of low-rank Gaussian mixtures ⋮ Statistical inference for structured high-dimensional models. Abstracts from the workshop held March 11--17, 2018 ⋮ Normal approximation and confidence region of singular subspaces ⋮ Robust tensor CUR decompositions: rapid low-Tucker-rank tensor recovery with sparse corruptions ⋮ Model-Based Tensor Low-Rank Clustering ⋮ Subspace estimation from unbalanced and incomplete data matrices: \({\ell_{2,\infty}}\) statistical guarantees ⋮ Robust Low-Rank Tensor Decomposition with the L ₂ Criterion ⋮ Block structure-based covariance tensor decomposition for group identification in matrix variables ⋮ Community detection on mixture multilayer networks via regularized tensor decomposition ⋮ Unnamed Item

Uses Software

• BrainWeb

Cites Work

• Unnamed Item
• Tensor Decompositions and Applications
• On tensor completion via nuclear norm minimization
• Estimation of high-dimensional low-rank matrices
• Multiarray signal processing: tensor decomposition meets compressed sensing
• Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
• On polynomial time methods for exact low-rank tensor completion
• Complexity of random smooth functions on the high-dimensional sphere
• Noisy low-rank matrix completion with general sampling distribution
• A Block Coordinate Descent Method for Regularized Multiconvex Optimization with Applications to Nonnegative Tensor Factorization and Completion
• Local Convergence of the Alternating Least Squares Algorithm for Canonical Tensor Approximation
• Tensor decompositions for learning latent variable models
• A Multilinear Singular Value Decomposition
• Incoherent Tensor Norms and Their Applications in Higher Order Tensor Completion
• Tensor Algebra and Multidimensional Harmonic Retrieval in Signal Processing for MIMO Radar
• Tensor-Based Formulation and Nuclear Norm Regularization for Multienergy Computed Tomography
• Random Matrices and Complexity of Spin Glasses
• Spectral Algorithms for Tensor Completion
• Tensor Rank and the Ill-Posedness of the Best Low-Rank Approximation Problem
• Most Tensor Problems Are NP-Hard
• Perturbation bounds in connection with singular value decomposition

This page was built for publication: Statistically optimal and computationally efficient low rank tensor completion from noisy entries