GRADIENT PROJECTION METHODS FOR THE n-COUPLING PROBLEM

Kum, Sangho;Yun, Sangwoon

• Accepted : 2018.08.29
• Published : 2019.07.01
• 20 0

Abstract

We are concerned with optimization methods for the $L^2$-Wasserstein least squares problem of Gaussian measures (alternatively the n-coupling problem). Based on its equivalent form on the convex cone of positive definite matrices of fixed size and the strict convexity of the variance function, we are able to present an implementable (accelerated) gradient method for finding the unique minimizer. Its global convergence rate analysis is provided according to the derived upper bound of Lipschitz constants of the gradient function.

Keywords

$L^2$-Wasserstein least squares problem;n-coupling problem;Gaussian measure;positive definite matrix;Nesterov-Todd scaling;gradient projection method

Acknowledgement

Supported by : NRF