Simultaneously Structured Models With Application to Sparse and Low-Rank Matrices
From MaRDI portal
Abstract: The topic of recovery of a structured model given a small number of linear observations has been well-studied in recent years. Examples include recovering sparse or group-sparse vectors, low-rank matrices, and the sum of sparse and low-rank matrices, among others. In various applications in signal processing and machine learning, the model of interest is known to be structured in several ways at the same time, for example, a matrix that is simultaneously sparse and low-rank. Often norms that promote each individual structure are known, and allow for recovery using an order-wise optimal number of measurements (e.g., norm for sparsity, nuclear norm for matrix rank). Hence, it is reasonable to minimize a combination of such norms. We show that, surprisingly, if we use multi-objective optimization with these norms, then we can do no better, order-wise, than an algorithm that exploits only one of the present structures. This result suggests that to fully exploit the multiple structures, we need an entirely new convex relaxation, i.e. not one that is a function of the convex relaxations used for each structure. We then specialize our results to the case of sparse and low-rank matrices. We show that a nonconvex formulation of the problem can recover the model from very few measurements, which is on the order of the degrees of freedom of the matrix, whereas the convex problem obtained from a combination of the and nuclear norms requires many more measurements. This proves an order-wise gap between the performance of the convex and nonconvex recovery problems in this case. Our framework applies to arbitrary structure-inducing norms as well as to a wide range of measurement ensembles. This allows us to give performance bounds for problems such as sparse phase retrieval and low-rank tensor completion.
Cited in
(47)- Tensor train rank minimization with hybrid smoothness regularization for visual data recovery
- Compressive total variation for image reconstruction and restoration
- Sparse model uncertainties in compressed sensing with application to convolutions and sporadic communication
- Jointly low-rank and bisparse recovery: questions and partial answers
- Joint structure-texture low-dimensional modeling for image decomposition with a plug-and-play framework
- Convex relaxation algorithm for a structured simultaneous low-rank and sparse recovery problem
- Compressive phase retrieval: Optimal sample complexity with deep generative priors
- Lifting for blind deconvolution in random mask imaging: identifiability and convex relaxation
- Sparse power factorization: balancing peakiness and sample complexity
- Isolated calmness of solution mappings and exact recovery conditions for nuclear norm optimization problems
- Tensor theta norms and low rank recovery
- Solving equations of random convex functions via anchored regression
- Self-calibration and biconvex compressive sensing
- An optimal statistical and computational framework for generalized tensor estimation
- Optimization on the hierarchical Tucker manifold - applications to tensor completion
- Low-rank approximation and completion of positive tensors
- Low complexity regularization of linear inverse problems
- A geometric analysis of phase retrieval
- Constructing confidence intervals for the signals in sparse phase retrieval
- Equivalent Lipschitz surrogates for zero-norm and rank optimization problems
- Non-intrusive tensor reconstruction for high-dimensional random PDEs
- Recovering structured signals in noise: least-squares meets compressed sensing
- Sparse recovery from quadratic measurements with external field
- Sparse disjointed recovery from noninflating measurements
- Low-rank and joint-sparse signal recovery using sparse Bayesian learning in a WBAN
- Trace regression model with simultaneously low rank and row(column) sparse parameter
- Auto-calibration and biconvex compressive sensing with applications to parallel MRI
- Sharp MSE bounds for proximal denoising
- Sparse and low-rank covariance matrix estimation
- Riemannian thresholding methods for row-sparse and low-rank matrix recovery
- An Unbiased Approach to Low Rank Recovery
- A VMiPG method for composite optimization with nonsmooth term having no closed-form proximal mapping
- Generic error bounds for the generalized Lasso with sub-exponential data
- Tensor completion based on triple tubal nuclear norm
- Enhanced image approximation using shifted rank-1 reconstruction
- Extreme point inequalities and geometry of the rank sparsity ball
- Sharp optimality of sparse group LASSO and SLOPE under weaker assumptions
- Robust sensing of low-rank matrices with non-orthogonal sparse decomposition
- Sparse Matrix Graphical Models
- An efficient asymptotic DC method for sparse and low-rank matrix recovery
- Robust recovery of low-rank matrices with non-orthogonal sparse decomposition from incomplete measurements
- Convex and Nonconvex Optimization Are Both Minimax-Optimal for Noisy Blind Deconvolution Under Random Designs
- Flavors of compressive sensing
- Proof methods for robust low-rank matrix recovery
- Near-optimal estimation of simultaneously sparse and low-rank matrices from nested linear measurements
- A convex variational model for learning convolutional image atoms from incomplete data
- Subspace clustering by \((k,k)\)-sparse matrix factorization
This page was built for publication: Simultaneously Structured Models With Application to Sparse and Low-Rank Matrices
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2978654)
