Iterative hard thresholding for low CP-rank tensor models
From MaRDI portal
Publication:6042723
Abstract: Recovery of low-rank matrices from a small number of linear measurements is now well-known to be possible under various model assumptions on the measurements. Such results demonstrate robustness and are backed with provable theoretical guarantees. However, extensions to tensor recovery have only recently began to be studied and developed, despite an abundance of practical tensor applications. Recently, a tensor variant of the Iterative Hard Thresholding method was proposed and theoretical results were obtained that guarantee exact recovery of tensors with low Tucker rank. In this paper, we utilize the same tensor version of the Restricted Isometry Property (RIP) to extend these results for tensors with low CANDECOMP/PARAFAC (CP) rank. In doing so, we leverage recent results on efficient approximations of CP decompositions that remove the need for challenging assumptions in prior works. We complement our theoretical findings with empirical results that showcase the potential of the approach.
Recommendations
- Low rank tensor recovery via iterative hard thresholding
- Iterative methods based on soft thresholding of hierarchical tensors
- Iterative \(p\)-shrinkage thresholding algorithm for low Tucker rank tensor recovery
- Low-rank tensor recovery using sequentially optimal modal projections in iterative hard thresholding (SeMPIHT)
- Iterative hard thresholding for low-rank recovery from rank-one projections
- Minimum n-rank approximation via iterative hard thresholding
- A Fixed Point Iterative Method for Low $n$-Rank Tensor Pursuit
- Fast randomized tensor singular value thresholding for low‐rank tensor optimization
- Recovering low CP/Tucker ranked tensors, with applications in tensor completion
- Low-CP-rank tensor completion via practical regularization
Cites work
- A mathematical introduction to compressive sensing
- A Multilinear Singular Value Decomposition
- Analysis of individual differences in multidimensional scaling via an \(n\)-way generalization of ``Eckart-Young decomposition
- Compressive Multiplexing of Correlated Signals
- Decoding by Linear Programming
- Efficient Tensor Completion for Color Image and Video Recovery: Low-Rank Tensor Train
- Exact matrix completion via convex optimization
- Factorization strategies for third-order tensors
- From quantum to classical molecular dynamics: Reduced models and numerical analysis.
- Greedy low-rank approximation in Tucker format of solutions of tensor linear systems
- Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization
- scientific article; zbMATH DE number 3282420 (Why is no real title available?)
- Invertibility of symmetric random matrices
- Iterative hard thresholding for compressed sensing
- Linear Convergence of Stochastic Iterative Greedy Algorithms With Sparse Constraints
- Low rank tensor recovery via iterative hard thresholding
- Most tensor problems are NP-hard
- Normalized iterative hard thresholding for matrix completion
- Relative error tensor low rank approximation
- Robust principal component analysis?
- Tensor Decompositions and Applications
- Tensor decompositions for learning latent variable models
- Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements
- Uniqueness conditions for low-rank matrix recovery
Cited in
(12)- RIP-based performance guarantee for low-tubal-rank tensor recovery
- Low rank tensor recovery via iterative hard thresholding
- Recovering low CP/Tucker ranked tensors, with applications in tensor completion
- Minimum n-rank approximation via iterative hard thresholding
- Tensor completion in hierarchical tensor representations
- On identity testing of tensors, low-rank recovery and compressed sensing
- Low-rank tensor recovery using sequentially optimal modal projections in iterative hard thresholding (SeMPIHT)
- Modewise operators, the tensor restricted isometry property, and low-rank tensor recovery
- Iterative singular tube hard thresholding algorithms for tensor recovery
- Near-optimal tensor recovery guarantees for transformed total variation minimization
- Tensor recovery from quantized measurements based on modewise operators
- Linear convergence of reshuffling Kaczmarz methods with sparse constraints
This page was built for publication: Iterative hard thresholding for low CP-rank tensor models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6042723)
