Browse > Article
http://dx.doi.org/10.4134/JKMS.j180517

GRADIENT PROJECTION METHODS FOR THE n-COUPLING PROBLEM  

Kum, Sangho (Department of Mathematics Education Chungbuk National University)
Yun, Sangwoon (Department of Mathematics Education Sungkyunkwan University)
Publication Information
Journal of the Korean Mathematical Society / v.56, no.4, 2019 , pp. 1001-1016 More about this Journal
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;
Citations & Related Records
연도 인용수 순위
  • Reference
1 P. Tseng, On accelerated proximal gradient methods for convex-concave optimization Preprint http://www.mit.edu/-dimitrib/PTseng/papers/apgm.pdf, 2008.
2 C. Villani, Topics in Optimal Transportation, Graduate Studies in Mathematics, 58, American Mathematical Society, Providence, RI, 2003.
3 C. Villani, Optimal Transport, Grundlehren der Mathematischen Wissenschaften, 338, Springer-Verlag, Berlin, 2009.
4 M. Knott and C. S. Smith, On a generalization of cyclic monotonicity and distances among random vectors, Linear Algebra Appl. 199 (1994), 363-371.   DOI
5 J. Lawson and Y. Lim, Monotonic properties of the least squares mean, Math. Ann. 351 (2011), no. 2, 267-279.   DOI
6 J. Lawson and Y. Lim, Weighted means and Karcher equations of positive operators, Proc. Natl. Acad. Sci. USA 110 (2013), no. 39, 15626-15632.   DOI
7 A. S. Lewis and J. Malick, Alternating projections on manifolds, Math. Oper. Res. 33 (2008), no. 1, 216-234.   DOI
8 R. J. McCann, A convexity principle for interacting gases, Adv. Math. 128 (1997), no. 1, 153-179.   DOI
9 A. Nedic and D. P. Bertsekas, Incremental subgradient methods for nondifferentiable optimization, SIAM J. Optim. 12 (2001), no. 1, 109-138.   DOI
10 Yu. Nesterov, Smooth minimization of non-smooth functions, Math. Program. 103 (2005), no. 1, Ser. A, 127-152.   DOI
11 I. Olkin and F. Pukelsheim, The distance between two random vectors with given dispersion matrices, Linear Algebra Appl. 48 (1982), 257-263.   DOI
12 J. Rabin, G. Peyre, J. Delon, and M. Bernot, Wasserstein Barycenter and Its Application to Texture Mixing, 435-446, Springer, Berlin, Heidelberg, 2012.
13 L. Ruschendorf and L. Uckelmann, On the n-coupling problem, J. Multivariate Anal. 81 (2002), no. 2, 242-258.   DOI
14 D. P. Bertsekas, Nonlinear Programming, second edition, Athena Scientific Optimization and Computation Series, Athena Scientific, Belmont, MA, 1999.
15 M. Agueh and G. Carlier, Barycenters in the Wasserstein space, SIAM J. Math. Anal. 43 (2011), no. 2, 904-924.   DOI
16 P. C. Alvarez Esteban, E. del Barrio, J. Cuesta-Albertos, and C. Matran, A fixed-point approach to barycenters in Wasserstein space, J. Math. Anal. Appl. 441 (2016), no. 2, 744-762.   DOI
17 M. Bacak, Computing medians and means in Hadamard spaces, SIAM J. Optim. 24 (2014), no. 3, 1542-1566.   DOI
18 D. P. Bertsekas, Incremental gradient, subgradient, and proximal methods for convex optimization: A survey, Preprint arXiv:1507.01030, 2015.
19 R. Bhatia, T. Jain, and Y. Lim, On the bures-wasserstein distance between positive definite matrices, preprint.
20 J. Bigot and T. Klein, Consistent estimation of a population barycenter in the wasserstein space, Preprint arXiv:1212.2562, 2012.
21 Y. Brenier, Polar factorization and monotone rearrangement of vector-valued functions, Comm. Pure Appl. Math. 44 (1991), no. 4, 375-417.   DOI
22 G. Carlier and I. Ekeland, Matching for teams, Econom. Theory 42 (2010), no. 2, 397-418.   DOI
23 G. Carlier, A. Oberman, and E. Oudet, Numerical methods for matching for teams and Wasserstein barycenters, ESAIM Math. Model. Numer. Anal. 49 (2015), no. 6, 1621-1642.   DOI
24 C. R. Givens and R. M. Shortt, A class of Wasserstein metrics for probability distributions, Michigan Math. J. 31 (1984), no. 2, 231-240.   DOI
25 D. C. Dowson and B. V. Landau, The Frechet distance between multivariate normal distributions, J. Multivariate Anal. 12 (1982), no. 3, 450-455.   DOI
26 W. Gangbo and R. J. McCann, The geometry of optimal transportation, Acta Math. 177 (1996), no. 2, 113-161.   DOI
27 W. Gangbo and A. Swiech, Optimal maps for the multidimensional Monge-Kantorovich problem, Comm. Pure Appl. Math. 51 (1998), no. 1, 23-45.   DOI
28 M. Ito and M. Fukuda, A family of subgradient-based methods for convex optimization problems in a unifying framework, Optim. Methods Softw. 31 (2016), no. 5, 952-982.   DOI
29 R. Bhatia, Matrix Analysis, Graduate Texts in Mathematics, 169, Springer-Verlag, New York, 1997.
30 L. Kantorovich and G. Rubinstein, On a space of completely additive functions, Vestn. Lenin. Univ. 13 (1958), 52-59.