• Title/Summary/Keyword: $L^2$-Wasserstein least squares problem

Search Result 2, Processing Time 0.019 seconds

STOCHASTIC GRADIENT METHODS FOR L2-WASSERSTEIN LEAST SQUARES PROBLEM OF GAUSSIAN MEASURES

  • YUN, SANGWOON;SUN, XIANG;CHOI, JUNG-IL
    • Journal of the Korean Society for Industrial and Applied Mathematics
    • /
    • v.25 no.4
    • /
    • pp.162-172
    • /
    • 2021
  • This paper proposes stochastic methods to find an approximate solution for the L2-Wasserstein least squares problem of Gaussian measures. The variable for the problem is in a set of positive definite matrices. The first proposed stochastic method is a type of classical stochastic gradient methods combined with projection and the second one is a type of variance reduced methods with projection. Their global convergence are analyzed by using the framework of proximal stochastic gradient methods. The convergence of the classical stochastic gradient method combined with projection is established by using diminishing learning rate rule in which the learning rate decreases as the epoch increases but that of the variance reduced method with projection can be established by using constant learning rate. The numerical results show that the present algorithms with a proper learning rate outperforms a gradient projection method.

GRADIENT PROJECTION METHODS FOR THE n-COUPLING PROBLEM

  • Kum, Sangho;Yun, Sangwoon
    • Journal of the Korean Mathematical Society
    • /
    • v.56 no.4
    • /
    • pp.1001-1016
    • /
    • 2019
  • 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.