Finding a sparse vector in a subspace: Linear sparsity using alternating directions

Abstract

Is it possible to find the sparsest vector (direction) in a generic subspace $\mathcal{S}\subseteq {\mathbb{R}}^p$ with $\dim (\mathcal{S})=n<p$? This problem can be considered a homogeneous variant of the sparse recovery problem, and finds connections to sparse dictionary learning, sparse PCA, and many other problems in signal processing and machine learning. In this paper, we focus on a **planted sparse model** for the subspace: the target sparse vector is embedded in an otherwise random subspace. Simple convex heuristics for this planted recovery problem provably break down when the fraction of nonzero entries in the target sparse vector substantially exceeds $O(1/\sqrt{n})$. In contrast, we exhibit a relatively simple nonconvex approach based on alternating directions, which provably succeeds even when the fraction of nonzero entries is $\Omega (1)$. To the best of our knowledge, this is the first practical algorithm to achieve linear scaling under the planted sparse model. Empirically, our proposed algorithm also succeeds in more challenging data models, e.g., sparse dictionary learning.

Accepted by IEEE Trans. Information Theory. The paper has been revised by the reviewers' comments. The proofs have been streamlined

References in corpus (1)

• Phase Retrieval via Wirtinger Flow: Theory and Algorithms

Cited by in corpus (7)

• Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
• A Geometric Analysis of Phase Retrieval
• An Overview of Robust Subspace Recovery
• Computational inverse method for constructing spaces of quantum models from wave functions
• Tower of quantum scars in a partially many-body localized system
• Unique sparse decomposition of low rank matrices
• Manifold Proximal Point Algorithms for Dual Principal Component Pursuit and Orthogonal Dictionary Learning