Improved Sparse Low-Rank Matrix Estimation
arXiv:1605.00042 · doi:10.1016/j.sigpro.2017.04.011
Abstract
We address the problem of estimating a sparse low-rank matrix from its noisy observation. We propose an objective function consisting of a data-fidelity term and two parameterized non-convex penalty functions. Further, we show how to set the parameters of the non-convex penalty functions, in order to ensure that the objective function is strictly convex. The proposed objective function better estimates sparse low-rank matrices than a convex method which utilizes the sum of the nuclear norm and the norm. We derive an algorithm (as an instance of ADMM) to solve the proposed problem, and guarantee its convergence provided the scalar augmented Lagrangian parameter is set appropriately. We demonstrate the proposed method for denoising an audio signal and an adjacency matrix representing protein interactions in the `Escherichia coli' bacteria.
arXiv comment10 pages, 10 figures
References in corpus (17)
- The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices
- Fast Image Recovery Using Variable Splitting and Constrained Optimization
- Rank-Sparsity Incoherence for Matrix Decomposition
- Generalized Forward-Backward Splitting
- Generalized Nonconvex Nonsmooth Low-Rank Minimization
- Operator norm consistent estimation of large-dimensional sparse covariance matrices
- Global Convergence of ADMM in Nonconvex Nonsmooth Optimization
- Sparse Signal Estimation by Maximally Sparse Convex Optimization
- OptShrink: An algorithm for improved low-rank signal matrix denoising by optimal, data-driven singular value shrinkage
- Simultaneously sparse and low-rank abundance matrix estimation for hyperspectral image unmixing
- Total Variation Denoising via the Moreau Envelope
- Enhanced Low-Rank Matrix Approximation
- Joint variable and rank selection for parsimonious estimation of high-dimensional matrices
- Convex Denoising using Non-Convex Tight Frame Regularization
- Generalized Singular Value Thresholding
- Background Subtraction via Generalized Fused Lasso Foreground Modeling
- Link Prediction in Graphs with Autoregressive Features