Abstract
We consider a point cloud \(X_n := \{ {\mathbf {x}}_1, \ldots , {\mathbf {x}}_n \}\) uniformly distributed on the flat torus \({\mathbb {T}}^d : = \mathbb {R}^d / \mathbb {Z}^d \), and construct a geometric graph on the cloud by connecting points that are within distance \(\varepsilon \) of each other. We let \({\mathcal {P}}(X_n)\) be the space of probability measures on \(X_n\) and endow it with a discrete Wasserstein distance \(W_n\) as introduced independently in Chow et al. (Arch Ration Mech Anal 203:969–1008, 2012), Maas (J Funct Anal 261:2250–2292, 2011) and Mielke (Nonlinearity 24:1329–1346, 2011) for general finite Markov chains. We show that as long as \(\varepsilon = \varepsilon _n\) decays towards zero slower than an explicit rate depending on the level of uniformity of \(X_n\), then the space \(({\mathcal {P}}(X_n), W_n)\) converges in the Gromov–Hausdorff sense towards the space of probability measures on \({\mathbb {T}}^d\) endowed with the Wasserstein distance. The analysis presented in this paper is a first step in the study of stability of evolution equations defined over random point clouds as the number of points grows to infinity.
Similar content being viewed by others
References
Ambrosio, L., Gigli, N., Savaré, G.: Gradient Flows in Metric Spaces and in the Space of Probability Measures, Lectures in Mathematics. ETH Zürich, Basel (2005)
Benamou, J.-D., Brenier, Y.: A computational fluid mechanics solution to the Monge–Kantorovich mass transfer problem. Numer. Math. 84, 375–393 (2000)
Burago, D., Burago, Y., Ivanov, S.: A Course in Metric Geometry, Graduate Studies in Mathematics, vol. 33. American Mathematical Society, Providence (2001)
Burago, D., Ivanov, S., Kurylev, Y.: A graph discretization of the Laplace–Beltrami operator. J. Spectr. Theory 4, 675–714 (2014)
Calder, J.: Consistency of Lipschitz learning with infinite unlabeled data and finite labeled data, arXiv preprint arXiv:1710.10364 (2017)
Calder, J.: The game theoretic p-Laplacian and semi-supervised learning with few labels. Nonlinearity 32, 301 (2018)
Calder, J., Slepcev, D.: Properly-weighted graph Laplacian for semi-supervised learning, arXiv preprint arXiv:1810.04351 (2018)
Carreira-Perpiñán, M.Á: A review of mean-shift algorithms for clustering. CoRR, arXiv:1503.00687 (2015)
Champion, T., De Pascale, L., Juutinen, P.: The \(\infty \)-Wasserstein distance: local solutions and existence of optimal transport maps. SIAM J. Math. Anal. 40, 1–20 (2008)
Chow, S.-N., Huang, W., Li, Y., Zhou, H.: Fokker–Planck equations for a free energy functional or Markov process on a graph. Arch. Ration. Mech. Anal. 203, 969–1008 (2012)
Coifman, R.R., Lafon, S.: Diffusion maps. Appl. Comput. Harmon. Anal. 21, 5–30 (2006). (special issue: diffusion maps and wavelets)
Davis, E., Sethuraman, S.: Approximating geodesics via random points. Ann. Appl. Probab. 29, 1446–1486 (2019)
El Alaoui, A., Cheng, X., Ramdas, A., Wainwright, M.J., Jordan, M.I.: Asymptotic behavior of \( l^p\)-based laplacian regularization in semi-supervised learning. In: Conference on Learning Theory, pp. 879–906 (2016)
Erbar, M., Fathi, M., Laschos, V., Schlichting, A.: Gradient flow structure for Mckean–Vlasov equations on discrete spaces. Discrete Contin. Dyn. Syst. A 36(12), 6799–6833 (2016). https://doi.org/10.3934/dcds.2016096
Erbar, M., Kopfer, E.: Super RICCI flows for weighted graphs. arXiv preprint arXiv:1805.06703 (2018)
Erbar, M., Maas, J.: Gradient flow structures for discrete porous medium equations. Discrete Contin. Dyn. Syst. A 34, 1355–1374 (2014)
Erbar, M., Maas, J.: Ricci curvature of finite markov chains via convexity of the entropy. Arch. Ration. Mech. Anal. 206, 997–1038 (2012)
Erbar, M., Maas, J., Wirth, M.: On the geometry of geodesics in discrete optimal transport. Calc. Var. Partial Differ. Equ. 58, 19 (2018)
Fathi, M., Maas, J.: Entropic ricci curvature bounds for discrete interacting systems. Ann. Appl. Probab. 26, 1774–1806 (2016)
García Trillos, N., Slepčev, D.: On the rate of convergence of empirical measures in \(\infty \)-transportation distance. Can. J. Math. 67, 1358–1383 (2015)
Gigli, N.: On the heat flow on metric measure spaces: existence, uniqueness and stability. Calc. Var. Partial Differ. Equ. 39, 101–120 (2010)
Gigli, N., Maas, J.: Gromov–Hausdorff convergence of discrete transportation metrics. SIAM J. Math. Anal. 45, 879–899 (2013)
Gladbach, P., Kopfer, E., Maas, J.: Scaling limits of discrete optimal transport (2018)
Hwang, S.J., Damelin, S.B., Hero III, A.O.: Shortest path through random points. Ann. Appl. Probab. 26, 2791–2823 (2016)
Jordan, R., Kinderlehrer, D., Otto, F.: The variational formulation of the Fokker–Planck equation. SIAM J. Math. Anal. 29, 1–17 (1998)
Maas, J.: Gradient flows of the entropy for finite Markov chains. J. Funct. Anal. 261, 2250–2292 (2011)
Maas, J., Matthes, D.: Long-time behavior of a finite volume discretization for a fourth order diffusion equation. Nonlinearity 29, 1992–2023 (2016)
Mielke, A.: A gradient structure for reaction–diffusion systems and for energy-drift-diffusion systems. Nonlinearity 24, 1329–1346 (2011)
Mielke, A.: Geodesic convexity of the relative entropy in reversible Markov chains. Calc. Var. Partial Differ. Equ. 48, 1–31 (2013)
Sandier, E., Serfaty, S.: Gamma-convergence of gradient flows with applications to Ginzburg-Landau. Commun. Pure Appl. Math. 57, 1627–1672 (2004)
Slepcev, D., Thorpe, M.: Analysis of p-Laplacian regularization in semi-supervised learning, arXiv preprint arXiv:1707.06213 (2017)
Smola, A.J., Kondor, R.: Kernels and regularization on graphs. In: Schölkopf B., Warmuth M.K. (eds.) Learning Theory and Kernel Machines. Springer, Berlin, Heidelberg, pp. 144–158 (2003)
Szlam, A., Bresson, X.: A total variation-based graph clustering algorithm for cheeger ratio cuts. UCLA CAM Report 1–12 (2009)
Trillos, N.G., Gerlach, M., Hein, M., Slepčev, D.: Spectral convergence of the graph Laplacian on random geometric graphs towards the Laplace Beltrami operator (in preparation) (2018)
Trillos, N.G., Slepčev, D.: Continuum limit of total variation on point clouds. Arch. Ration. Mech. Anal. 220, 193–241 (2016)
Trillos, N.G., Slepčev, D.: A variational approach to the consistency of spectral clustering. Appl. Comput. Harmon. Anal. 45, 239–281 (2018)
Trillos, N.G., Slepčev, D., von Brecht, J., Laurent, T., Bresson, X.: Consistency of cheeger and ratio graph cuts. J. Mach. Learn. Res. 17, 1–46 (2016)
von Luxburg, U.: A tutorial on spectral clustering. Stat. Comput. 17, 395–416 (2007)
Wang, Y.-X., Sharpnack, J., Smola, A.J., Tibshirani, R.J.: Trend filtering on graphs. J. Mach. Learn. Res. 17, 3651–3691 (2016)
Acknowledgements
The author would like to thank Dejan Slepčev for enlightening discussions and for introducing him to the line of research investigated in this work. The author would also like to thank Jan Maas for enlightening discussions on this and other related topics. This manuscript was completed while the author was visiting the Erwin Schrödinger Institute to participate in the workshop “Optimal Transport: from Geometry to Numerics”. The author wants to thank the Institute for hospitality. Finally, the author would like to thank the anonymous referees for their suggestions.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by M. Struwe.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.