Normalized iterative hard thresholding for matrix completion
From MaRDI portal
Matrices of low rank can be uniquely determined from fewer linear measurements, or entries, than the total number of entries in the matrix. The authors propose an alternating projection algorithm which uses an adaptive step size calculated to be exact for a restricted subspace. The proposed method has near-optimal order recovery guarantees from dense measurement masks and average case performance superior in some respects to other matrix completion algorithms for dense measurement masks and entry measurements. The proposed algorithm is able to recover matrices from extremely close to the minimum number of measurements necessary.
Recommendations
- Matrix completion by singular value thresholding: sharp bounds
- Iterative hard thresholding for low-rank recovery from rank-one projections
- A Singular Value Thresholding Algorithm for Matrix Completion
- Low-rank matrix recovery via iteratively reweighted least squares minimization
- Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithm
Cited in
(51)- Painless breakups -- efficient demixing of low rank matrices
- The two-stage iteration algorithms based on the shortest distance for low-rank matrix completion
- Matrix completion under interval uncertainty
- Fast and provable algorithms for spectrally sparse signal reconstruction via low-rank Hankel matrix completion
- Low-rank approximation algorithms for matrix completion with random sampling
- Nonlinear matrix recovery using optimization on the Grassmann manifold
- Guarantees of Riemannian optimization for low rank matrix completion
- Parametrized quasi-soft thresholding operator for compressed sensing and matrix completion
- Matrix recipes for hard thresholding methods
- Homotopy method for matrix rank minimization based on the matrix hard thresholding method
- A non-convex algorithm framework based on DC programming and DCA for matrix completion
- Iterative hard thresholding for low-rank recovery from rank-one projections
- Transformed Schatten-1 iterative thresholding algorithms for low rank matrix completion
- Newton-type optimal thresholding algorithms for sparse optimization problems
- Regularized sample average approximation for high-dimensional stochastic optimization under low-rankness
- Compressed sensing of low-rank plus sparse matrices
- Adaptive iterative hard thresholding for low-rank matrix recovery and rank-one measurements
- Guarantees of Riemannian optimization for low rank matrix recovery
- Fast and near-optimal matrix completion via randomized basis pursuit
- Tensor completion in hierarchical tensor representations
- Harmonic mean iteratively reweighted least squares for low-rank matrix recovery
- An iterative hard thresholding estimator for low rank matrix recovery with explicit limiting distribution
- CGIHT: conjugate gradient iterative hard thresholding for compressed sensing and matrix completion
- Stable low-rank matrix recovery via null space properties
- Iterative hard thresholding methods for \(l_0\) regularized convex cone programming
- Minimax risk of matrix denoising by singular value thresholding
- Near-optimal matrix recovery from random linear measurements
- Rank $2r$ Iterative Least Squares: Efficient Recovery of Ill-Conditioned Low Rank Matrices from Few Entries
- Two modified algorithms for matrix completion using hard-thresholding algorithm
- Matrix rigidity and the ill-posedness of robust PCA and matrix completion
- Tensor networks and hierarchical tensors for the solution of high-dimensional partial differential equations
- GNMR: a provable one-line algorithm for low rank matrix recovery
- scientific article; zbMATH DE number 7306912 (Why is no real title available?)
- Streaming principal component analysis from incomplete data
- Finding low-rank solutions via nonconvex matrix factorization, efficiently and provably
- Matrix completion via minimizing an approximate rank
- Low-rank tensor recovery using sequentially optimal modal projections in iterative hard thresholding (SeMPIHT)
- Iterative hard thresholding for low CP-rank tensor models
- Fast gradient method for low-rank matrix estimation
- Riemannian thresholding methods for row-sparse and low-rank matrix recovery
- Modewise operators, the tensor restricted isometry property, and low-rank tensor recovery
- Stochastic variance reduced gradient for affine rank minimization problem
- Empirical Bayes Poisson matrix completion
- From theoretical guarantee to practical performance: selectable and optimal step-lengths for IHT and HTP algorithms in compressed sensing
- A preconditioned Riemannian gradient descent algorithm for low-rank matrix recovery
- Sufficient condition based on nearly optimal order RIC for IHT algorithm
- Projected Landweber iteration for matrix completion
- Chain-Linked Multiple Matrix Integration via Embedding Alignment
- Compressed Newton-direction-based thresholding methods for sparse optimization problems
- On trimming tensor-structured measurements and efficient low-rank tensor recovery
- Low rank matrix completion by alternating steepest descent methods
This page was built for publication: Normalized iterative hard thresholding for matrix completion
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2870672)
