Low rank tensor recovery via iterative hard thresholding

DOI10.1016/j.laa.2017.02.028zbMath1372.65130arXiv1602.05217OpenAlexW2963116674MaRDI QIDQ2400255

Željka Stojanac, Holger Rauhut, Reinhold Schneider

Publication date: 28 August 2017

Published in: Linear Algebra and its Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1602.05217

zbMATH Keywords

algorithmconvergencematrix completionnumerical experimentiterative hard thresholdingtensor completionhigher-order singular value decompositiontensor decompositionstensor train decompositionlow rank recoveryGaussian random ensemblehierarchical tensor formatrandom partial Fourier ensemble

Mathematics Subject Classification ID

Numerical solutions to overdetermined systems, pseudoinverses (65F20) Random matrices (algebraic aspects) (15B52) Multilinear algebra, tensor calculus (15A69) Matrix completion problems (15A83)

Related Items (38)

An optimal statistical and computational framework for generalized tensor estimation ⋮ Convergence bounds for empirical nonlinear least-squares ⋮ Tensor Regression Using Low-Rank and Sparse Tucker Decompositions ⋮ The numerics of phase retrieval ⋮ Inference for low-rank tensors -- no need to debias ⋮ Variants of Alternating Least Squares Tensor Completion in the Tensor Train Format ⋮ Tensor Completion in Hierarchical Tensor Representations ⋮ Nonconvex Low-Rank Tensor Completion from Noisy Data ⋮ Low-rank tensor completion by Riemannian optimization ⋮ Tensor completion by multi-rank via unitary transformation ⋮ Algebraic compressed sensing ⋮ Iterative hard thresholding for low CP-rank tensor models ⋮ $N$-Dimensional Tensor Completion for Nuclear Magnetic Resonance Relaxometry ⋮ Pricing High-Dimensional Bermudan Options with Hierarchical Tensor Formats ⋮ Modewise operators, the tensor restricted isometry property, and low-rank tensor recovery ⋮ Characterization of sampling patterns for low-tt-rank tensor retrieval ⋮ Polynomial approximation via compressed sensing of high-dimensional functions on lower sets ⋮ Quantized Compressed Sensing: A Survey ⋮ Cross: efficient low-rank tensor completion ⋮ Sampling-free Bayesian inversion with adaptive hierarchical tensor representations ⋮ Geometric Methods on Low-Rank Matrix and Tensor Manifolds ⋮ Tensor networks and hierarchical tensors for the solution of high-dimensional partial differential equations ⋮ Dimensionality reduction with subgaussian matrices: a unified theory ⋮ Low-Rank Tensor Recovery using Sequentially Optimal Modal Projections in Iterative Hard Thresholding (SeMPIHT) ⋮ On polynomial time methods for exact low-rank tensor completion ⋮ The convergence guarantee of the iterative hard thresholding algorithm with suboptimal feedbacks for large systems ⋮ Randomized interpolative decomposition of separated representations ⋮ Modified iterations for data-sparse solution of linear systems ⋮ Tensor theta norms and low rank recovery ⋮ Jointly low-rank and bisparse recovery: Questions and partial answers ⋮ Variational Monte Carlo -- bridging concepts of machine learning and high-dimensional partial differential equations ⋮ RIP-based performance guarantee for low-tubal-rank tensor recovery ⋮ Gradient-based optimization for regression in the functional tensor-train format ⋮ Endpoint Results for Fourier Integral Operators on Noncompact Symmetric Spaces ⋮ Non-intrusive tensor reconstruction for high-dimensional random PDEs ⋮ An iterative method for tensor inpainting based on higher-order singular value decomposition ⋮ Lower Memory Oblivious (Tensor) Subspace Embeddings with Fewer Random Bits: Modewise Methods for Least Squares ⋮ New Riemannian Preconditioned Algorithms for Tensor Completion via Polyadic Decomposition

Uses Software

• Tensorlab
• MCTDH

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Tensor-Train Decomposition
• Low rank matrix recovery from rank one measurements
• A mathematical introduction to compressive sensing
• Low-rank tensor completion by Riemannian optimization
• Dimensionality reduction with subgaussian matrices: a unified theory
• The density-matrix renormalization group in the age of matrix product states
• Iterative hard thresholding for compressed sensing
• Regularity of Gaussian processes
• Handwritten digit classification using higher order singular value decomposition
• From quantum to classical molecular dynamics: Reduced models and numerical analysis.
• Multidimensional filtering based on a tensor approach
• Majorizing measures without measures
• Tensor theta norms and low rank recovery
• A new scheme for the tensor representation
• Tail bounds via generic chaining
• The sizes of compact subsets of Hilbert space and continuity of Gaussian processes
• Exact matrix completion via convex optimization
• Low-Rank Matrix Completion by Riemannian Optimization
• Suprema of Chaos Processes and the Restricted Isometry Property
• Approximation Algorithms for Model-Based Compressive Sensing
• Compressive Multiplexing of Correlated Signals
• Hierarchical Singular Value Decomposition of Tensors
• Tensor completion and low-n-rank tensor recovery via convex optimization
• New and Improved Johnson–Lindenstrauss Embeddings via the Restricted Isometry Property
• Tensor Spaces and Numerical Tensor Calculus
• Breaking the Curse of Dimensionality, Or How to Use SVD in Many Dimensions
• Tensor rank is NP-complete
• Low-rank Matrix Recovery via Iteratively Reweighted Least Squares Minimization
• Tensor Completion in Hierarchical Tensor Representations
• Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• The Restricted Isometry Property of Subsampled Fourier Matrices
• Semidefinite Optimization and Convex Algebraic Geometry
• Structured random measurements in signal processing
• Isometric sketching of any set via the Restricted Isometry Property
• An Improved Estimate in the Restricted Isometry Problem
• Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements
• Recovering Low-Rank Matrices From Few Coefficients in Any Basis
• The Power of Convex Relaxation: Near-Optimal Matrix Completion
• Most Tensor Problems Are NP-Hard
• Upper and Lower Bounds for Stochastic Processes

This page was built for publication: Low rank tensor recovery via iterative hard thresholding