Augmented L1 and Nuclear-Norm Models with a Globally Linearly Convergent Algorithm

TL;DR

This paper introduces augmented L1 and nuclear-norm models with a globally linearly convergent algorithm, enabling efficient sparse and low-rank recovery with strong theoretical guarantees and explicit convergence rates.

Contribution

It proposes augmented models combining L1 and nuclear norms with quadratic terms, and establishes a globally linearly convergent algorithm with explicit rates for sparse and low-rank recovery.

Findings

Efficient recovery of sparse vectors and low-rank matrices using augmented models.

Global linear convergence of the proposed algorithm without requiring solution existence.

Explicit convergence rate provided for the linearized Bregman algorithm.

Abstract

This paper studies the long-existing idea of adding a nice smooth function to "smooth" a non-differentiable objective function in the context of sparse optimization, in particular, the minimization of $||x||_1+1/(2\alpha)||x||_2^2$, where $x$ is a vector, as well as the minimization of $||X||_*+1/(2\alpha)||X||_F^2$, where $X$ is a matrix and $||X||_*$ and $||X||_F$ are the nuclear and Frobenius norms of $X$, respectively. We show that they can efficiently recover sparse vectors and low-rank matrices. In particular, they enjoy exact and stable recovery guarantees similar to those known for minimizing $||x||_1$ and $||X||_*$ under the conditions on the sensing operator such as its null-space property, restricted isometry property, spherical section property, or RIPless property. To recover a (nearly) sparse vector $x^0$, minimizing $||x||_1+1/(2\alpha)||x||_2^2$ returns (nearly) the same solution as minimizing $||x||_1$ almost whenever $\alpha\ge 10||x^0||_\infty$. The same relation also holds between minimizing $||X||_*+1/(2\alpha)||X||_F^2$ and minimizing $||X||_*$ for recovering a (nearly) low-rank matrix $X^0$, if $\alpha\ge 10||X^0||_2$. Furthermore, we show that the linearized Bregman algorithm for minimizing $||x||_1+1/(2\alpha)||x||_2^2$ subject to $Ax=b$ enjoys global linear convergence as long as a nonzero solution exists, and we give an explicit rate of convergence. The convergence property does not require a solution solution or any properties on $A$. To our knowledge, this is the best known global convergence result for first-order sparse optimization algorithms.