# Compressed sensing of low-rank plus sparse matrices

arXiv: https://arxiv.org/abs/2007.09457 · HTML: https://mlsanity.com/paper/2007.09457/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2020.

## Built on by (most cited first, 6 of 6)

- [Compressed Smooth Sparse Decomposition](https://mlsanity.com/paper/2201.07404/) (2022)
- [Compressive Recovery of Sparse Precision Matrices](https://mlsanity.com/paper/2311.04673/) (2023)
- [A Dual Basis Approach for Structured Robust Euclidean Distance Geometry](https://mlsanity.com/paper/2505.18414/) (2025)
- [GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation](https://mlsanity.com/paper/2606.01412/) (2026)
- [Step and Smooth Decompositions as Topological Clustering](https://mlsanity.com/paper/2311.05756/) (2023)
- [Adversarial generalization of unfolding (model-based) networks](https://mlsanity.com/paper/2509.15370/) (2025)

## Abstract (arXiv)

Expressing a matrix as the sum of a low-rank matrix plus a sparse matrix is a flexible model capturing global and local features in data popularized as Robust PCA (Candes et al., 2011; Chandrasekaran et al., 2009). Compressed sensing, matrix completion, and their variants (Eldar and Kutyniok, 2012; Foucart and Rauhut, 2013) have established that data satisfying low complexity models can be efficiently measured and recovered from a number of measurements proportional to the model complexity rather than the ambient dimension. This manuscript develops similar guarantees showing that m× n matrices that can be expressed as the sum of a rank-r matrix and a s-sparse matrix can be recovered by computationally tractable methods from O(r(m+n-r)+s)log(mn/s) linear measurements. More specifically, we establish that the low-rank plus sparse matrix set is closed provided the incoherence of the low-rank component is upper bounded as μ<√mn/(r√s), and subsequently, the restricted isometry constants for the aforementioned matrices remain bounded independent of problem size provided p/mn, s/p, and r(m+n-r)/p remain fixed. Additionally, we show that semidefinite programming and two hard threshold gradient descent algorithms, NIHT and NAHT, converge to the measured matrix provided the measurement operator's RIC's are sufficiently small. These results also provably solve convex and non-convex formulation of Robust PCA with the asymptotically optimal fraction of corruptions α=Oleft(1/(μ r) right), where s = α2 mn, and improve the previously best known guarantees by not requiring that the fraction of corruptions is spread in every column and row by being upper bounded by α. Numerical experiments illustrating these results are shown for synthetic problems, dynamic-foreground/static-background separation, and multispectral imaging.