MLITJul 6, 2015

Subspace-Sparse Representation

arXiv:1507.01307v16 citations
Originality Incremental advance
AI Analysis

This work addresses a generalization of sparse recovery for subspace identification, with incremental improvements in theoretical conditions for applications like classification.

The paper tackles the problem of recovering a sparse representation that identifies the correct subspace when a signal lies in a low-dimensional subspace spanned by possibly linearly dependent dictionary columns, presenting sufficient conditions for subspace-sparse recovery that are less restrictive than the mutual coherence condition and applicable to traditional sparse recovery and classification methods.

Given an overcomplete dictionary $A$ and a signal $b$ that is a linear combination of a few linearly independent columns of $A$, classical sparse recovery theory deals with the problem of recovering the unique sparse representation $x$ such that $b = A x$. It is known that under certain conditions on $A$, $x$ can be recovered by the Basis Pursuit (BP) and the Orthogonal Matching Pursuit (OMP) algorithms. In this work, we consider the more general case where $b$ lies in a low-dimensional subspace spanned by some columns of $A$, which are possibly linearly dependent. In this case, the sparsest solution $x$ is generally not unique, and we study the problem that the representation $x$ identifies the subspace, i.e. the nonzero entries of $x$ correspond to dictionary atoms that are in the subspace. Such a representation $x$ is called subspace-sparse. We present sufficient conditions for guaranteeing subspace-sparse recovery, which have clear geometric interpretations and explain properties of subspace-sparse recovery. We also show that the sufficient conditions can be satisfied under a randomized model. Our results are applicable to the traditional sparse recovery problem and we get conditions for sparse recovery that are less restrictive than the canonical mutual coherent condition. We also use the results to analyze the sparse representation based classification (SRC) method, for which we get conditions to show its correctness.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes