Emergent Mind

Non-negative Least Squares via Overparametrization

(2207.08437)
Published Jul 18, 2022 in math.OC , cs.NA , and math.NA

Abstract

In many applications, solutions of numerical problems are required to be non-negative, e.g., when retrieving pixel intensity values or physical densities of a substance. In this context, non-negative least squares (NNLS) is a ubiquitous tool, e.g., when seeking sparse solutions of high-dimensional statistical problems. Despite vast efforts since the seminal work of Lawson and Hanson in the '70s, the non-negativity assumption is still an obstacle for the theoretical analysis and scalability of many off-the-shelf solvers. In the different context of deep neural networks, we recently started to see that the training of overparametrized models via gradient descent leads to surprising generalization properties and the retrieval of regularized solutions. In this paper, we prove that, by using an overparametrized formulation, NNLS solutions can reliably be approximated via vanilla gradient flow. We furthermore establish stability of the method against negative perturbations of the ground-truth. Our simulations confirm that this allows the use of vanilla gradient descent as a novel and scalable numerical solver for NNLS. From a conceptual point of view, our work proposes a novel approach to trading side-constraints in optimization problems against complexity of the optimization landscape, which does not build upon the concept of Lagrangian multipliers.

We're not able to analyze this paper right now due to high demand.

Please check back later (sorry!).

Generate a summary of this paper on our Pro plan:

We ran into a problem analyzing this paper.

Newsletter

Get summaries of trending comp sci papers delivered straight to your inbox:

Unsubscribe anytime.