Skip to main content
Log in

Entropic optimal transport: convergence of potentials

  • Published:
Probability Theory and Related Fields Aims and scope Submit manuscript

Abstract

We study the potential functions that determine the optimal density for \(\varepsilon \)-entropically regularized optimal transport, the so-called Schrödinger potentials, and their convergence to the counterparts in classical optimal transport, the Kantorovich potentials. In the limit \(\varepsilon \rightarrow 0\) of vanishing regularization, strong compactness holds in \(L^{1}\) and cluster points are Kantorovich potentials. In particular, the Schrödinger potentials converge in \(L^{1}\) to the Kantorovich potentials as soon as the latter are unique. These results are proved for all continuous, integrable cost functions on Polish spaces. In the language of Schrödinger bridges, the limit corresponds to the small-noise regime.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

Notes

  1. We mention that [19] uses the term Schrödinger potentials for \(f_{\varepsilon }/\varepsilon ,g_{\varepsilon }/\varepsilon \) in the Schrödinger bridge context, as is natural when no parameter \(\varepsilon \) is present. On the other hand, calling \(f_{\varepsilon },g_{\varepsilon }\) potentials is more convenient in our setting, well motivated by the connection with Kantorovich potentials in Theorem 1.1, and consistent with the terminology in [17].

  2. I.e., \(I^{*}\) is the (a.s. unique) measurable function satisfying \(I^{*}\ge I_{\lambda }\) a.s. for all \(\lambda \) and \(I^{*}\le J\) a.s. for any J satisfying \(J\ge I_{\lambda }\) a.s. for all \(\lambda \). In other words, \(I^{*}\) is the supremum in the lattice of measurable functions equipped with the a.s. order.

References

  1. Agueh, M., Carlier, G.: Barycenters in the Wasserstein space. SIAM J. Math. Anal. 43(2), 904–924 (2011)

    Article  MathSciNet  Google Scholar 

  2. Berman, R.J.: The Sinkhorn algorithm, parabolic optimal transport and geometric Monge–Ampère equations. Numer. Math. 145(4), 771–836 (2020)

    Article  MathSciNet  Google Scholar 

  3. Bernton, E., Ghosal, P., Nutz, M.: Entropic optimal transport: geometry and large deviations. Preprint arXiv:2102.04397v1 (2021)

  4. Beurling, A.: An automorphism of product measures. Ann. Math. 2(72), 189–200 (1960)

    Article  MathSciNet  Google Scholar 

  5. Borwein, J.M., Lewis, A.S.: Decomposition of multivariate functions. Canad. J. Math. 44(3), 463–482 (1992)

    Article  MathSciNet  Google Scholar 

  6. Borwein, J.M., Lewis, A.S., Nussbaum, R.D.: Entropy minimization, \(DAD\) problems, and doubly stochastic kernels. J. Funct. Anal. 123(2), 264–307 (1994)

    Article  MathSciNet  Google Scholar 

  7. Carlier, G.: On the linear convergence of the multi-marginal Sinkhorn algorithm. Preprint hal-03176512 (2021)

  8. Carlier, G., Duval, V., Peyré, G., Schmitzer, B.: Convergence of entropic schemes for optimal transport and gradient flows. SIAM J. Math. Anal. 49(2), 1385–1418 (2017)

    Article  MathSciNet  Google Scholar 

  9. Cominetti, R., San Martín, J.: Asymptotic analysis of the exponential penalty trajectory in linear programming. Math. Program. 67(2, Ser. A), 169–187 (1994)

    Article  MathSciNet  Google Scholar 

  10. Conforti, G., Tamanini, L.: A formula for the time derivative of the entropic cost and applications. J. Funct. Anal. 280(11), 108964 (2021)

    Article  MathSciNet  Google Scholar 

  11. Csiszár, I.: \(I\)-divergence geometry of probability distributions and minimization problems. Ann. Probab. 3, 146–158 (1975)

    Article  MathSciNet  Google Scholar 

  12. Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: Borges, O., Button, L., Welling, M., Ghahramani, Z., Weinberger, U.Q. (eds.) Advances in Neural Information Processing Systems, vol. 26, pp. 2292–2300 (2013)

  13. Dembo, A., Zeitouni, O.: Large Deviations Techniques and Applications, Volume 38 of Stochastic Modelling and Applied Probability. Springer, Berlin (2010). Corrected reprint of the second (1998) edition

  14. Di Marino, S., Gerolin, A.: An optimal transport approach for the Schrödinger bridge problem and convergence of Sinkhorn algorithm. J. Sci. Comput. 85(2), 27, 28 (2020)

    Article  Google Scholar 

  15. Föllmer, H.: Random fields and diffusion processes. In: Bold, A., Eckmann, B. (eds.) École d’Été de Probabilités de Saint-Flour XV-XVII, 1985–87. Lecture Notes in Mathematics, vol. 1362, pp. 101–203. Springer, Berlin (1988)

    Chapter  Google Scholar 

  16. Föllmer, H., Gantert, N.: Entropy minimization and Schrödinger processes in infinite dimensions. Ann. Probab. 25(2), 901–926 (1997)

    Article  MathSciNet  Google Scholar 

  17. Gigli, N., Tamanini, L.: Second order differentiation formula on \({\rm RCD}^{*}(K, N)\) spaces. J. Eur. Math. Soc. (JEMS) 23(5), 1727–1795 (2021)

    Article  MathSciNet  Google Scholar 

  18. Léonard, C.: From the Schrödinger problem to the Monge–Kantorovich problem. J. Funct. Anal. 262(4), 1879–1920 (2012)

    Article  MathSciNet  Google Scholar 

  19. Léonard, C.: A survey of the Schrödinger problem and some of its connections with optimal transport. Discrete Contin. Dyn. Syst. 34(4), 1533–1574 (2014)

    Article  MathSciNet  Google Scholar 

  20. Mena, G., Niles-Weed, J.: Statistical bounds for entropic optimal transport: sample complexity and the central limit theorem. In: Wallach, H., Larochelle, H., Beygelzimmer, A., d’Aldie’-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp. 4541–4551 (2019)

  21. Nutz. M.: Introduction to Entropic Optimal Transport. Lecture Notes. Columbia University (2021). https://www.math.columbia.edu/~mnutz/docs/EOT_lecture_notes.pdf

  22. Pal, S.: On the difference between entropic cost and the optimal transport cost. Preprint arXiv:1905.12206v1 (2019)

  23. Pennanen, T., Perkkiö, A.-P.: Convex duality in nonlinear optimal transport. J. Funct. Anal. 277(4), 1029–1060 (2019)

    Article  MathSciNet  Google Scholar 

  24. Peyré, G., Cuturi, M.: Computational optimal transport: with applications to data science. Found. Trends Mach. Learn. 11(5–6), 355–607 (2019)

    Article  Google Scholar 

  25. Rüschendorf, L., Thomsen, W.: Note on the Schrödinger equation and \(I\)-projections. Stat. Probab. Lett. 17(5), 369–375 (1993)

    Article  Google Scholar 

  26. Rüschendorf, L., Thomsen, W.: Closedness of sum spaces and the generalized Schrödinger problem. Teor. Veroyatnost. i Primenen. 42(3), 576–590 (1997)

    Article  MathSciNet  Google Scholar 

  27. Villani, C.: Optimal Transport, Old and New, Volume 338 of Grundlehren der Mathematischen Wissenschaften. Springer, Berlin (2009)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Marcel Nutz.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

The authors thank Guillaume Carlier, Giovanni Conforti, Soumik Pal and Luca Tamanini for helpful discussions.

MN acknowledges support by an Alfred P. Sloan Fellowship and NSF Grants DMS-1812661, DMS-2106056.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Nutz, M., Wiesel, J. Entropic optimal transport: convergence of potentials. Probab. Theory Relat. Fields 184, 401–424 (2022). https://doi.org/10.1007/s00440-021-01096-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00440-021-01096-8

Keywords

Mathematics Subject Classification

Navigation