Sparse Optimization on Measures with Over-parameterized Gradient Descent
Abstract
Minimizing a convex function of a measure with a sparsity-inducing penalty is a typical problem arising, e.g., in sparse spikes deconvolution or two-layer neural networks training. We show that this problem can be solved by discretizing the measure and running non-convex gradient descent on the positions and weights of the particles. For measures on a -dimensional manifold and under some non-degeneracy assumptions, this leads to a global optimization algorithm with a complexity scaling as in the desired accuracy , instead of for convex methods. The key theoretical tools are a local convergence analysis in Wasserstein space and an analysis of a perturbed mirror descent in the space of measures. Our bounds involve quantities that are exponential in which is unavoidable under our assumptions.
Cite
@article{arxiv.1907.10300,
title = {Sparse Optimization on Measures with Over-parameterized Gradient Descent},
author = {Lenaic Chizat},
journal= {arXiv preprint arXiv:1907.10300},
year = {2020}
}