Iteratively Reweighted Least Squares for Basis Pursuit with Global Linear Convergence Rate

Abstract

The recovery of sparse data is at the core of many applications in machine learning and signal processing. While such problems can be tackled using $\ell_1$-regularization as in the LASSO estimator and in the Basis Pursuit approach, specialized algorithms are typically required to solve the corresponding high-dimensional non-smooth optimization for large instances. Iteratively Reweighted Least Squares (IRLS) is a widely used algorithm for this purpose due its excellent numerical performance.
However, while existing theory is able to guarantee convergence of this algorithm to the minimizer, it does not provide a global convergence rate.

In this paper, we prove that a variant of IRLS converges with a global linear rate to a sparse solution, i.e., with a linear error decrease occurring immediately from any initialization, if the measurements fulfill the usual null space property assumption. We support our theory by numerical experiments showing that our linear rate captures the correct dimension dependence. We anticipate that our theoretical findings will lead to new insights for many other use cases of the IRLS algorithm, such as in low-rank matrix recovery.

Publication
In Neural Information Processing Systems (NeurIPS) 2021 (Spotlight, top 3% of submitted papers)
Christian Kümmerle
Christian Kümmerle
Postdoctoral Fellow