A Dictionary Based Generalization of Robust PCA
This work addresses robust data analysis for applications like signal processing by generalizing robust PCA with dictionary-based sparsity, but it is incremental as it extends existing methods to include dictionary constraints.
The paper tackles the problem of decomposing a data matrix into low-rank and dictionary-sparse components using convex demixing, showing successful recovery under mild assumptions up to a global sparsity level, with empirical validation through phase transitions in rank and sparsity for various dictionary sizes.
We analyze the decomposition of a data matrix, assumed to be a superposition of a low-rank component and a component which is sparse in a known dictionary, using a convex demixing method. We provide a unified analysis, encompassing both undercomplete and overcomplete dictionary cases, and show that the constituent components can be successfully recovered under some relatively mild assumptions up to a certain $\textit{global}$ sparsity level. Further, we corroborate our theoretical results by presenting empirical evaluations in terms of phase transitions in rank and sparsity for various dictionary sizes.