Skip to main content
Log in

On the Relation Between Optimal Transport and Schrödinger Bridges: A Stochastic Control Viewpoint

  • Published:
Journal of Optimization Theory and Applications Aims and scope Submit manuscript

Abstract

We take a new look at the relation between the optimal transport problem and the Schrödinger bridge problem from a stochastic control perspective. Our aim is to highlight new connections between the two that are richer and deeper than those previously described in the literature. We begin with an elementary derivation of the Benamou–Brenier fluid dynamic version of the optimal transport problem and provide, in parallel, a new fluid dynamic version of the Schrödinger bridge problem. We observe that the latter establishes an important connection with optimal transport without zero-noise limits and solves a question posed by Eric Carlen in 2006. Indeed, the two variational problems differ by a Fisher information functional. We motivate and consider a generalization of optimal mass transport in the form of a (fluid dynamic) problem of optimal transport with prior. This can be seen as the zero-noise limit of Schrödinger bridges when the prior is any Markovian evolution. We finally specialize to the Gaussian case and derive an explicit computational theory based on matrix Riccati differential equations. A numerical example involving Brownian particles is also provided.

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.

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Notes

  1. Over the years, several alternative versions of stochastic mechanics have been proposed by Fényes, Bohm–Vigier, Levy–Krener, Rosenbrock [2226] to name but a few.

  2. Therefore, W is not a probability measure. Its marginals at each point in time coincide with the Lebesgue measure.

  3. See [30, pp. 7–8] for a justification of employing unbounded path measures in relative entropy problems.

  4. Measure induced by \(\sqrt{\epsilon }w(t)\) on path space \(\varOmega \) with volume measure as initial condition.

  5. This calculation indicates that there may be a limit as \(\epsilon \searrow 0\) of \(\mathrm{inf}\{\epsilon H(Q_\epsilon ,P_\epsilon )\}\) and, hopefully, in suitable sense, of the minimizers. This is indeed the case; see [30, 33, 44] for a precise statement of limiting results.

References

  1. Monge, G.: Mémoire sur la théorie des déblais et des remblais, De l’Imprimerie Royale (1781)

  2. Schrödinger, E.: Über die Umkehrung der Naturgesetze, Sitzungsberichte der Preuss. Phys. Math. Klasse. 10, 144–153 (1931)

  3. Schrödinger, E.: Sur la théorie relativiste de l’electron et l’interpretation de la mécanique quantique. Ann. Inst. H. Poincaré. 2, 269 (1932)

    MATH  Google Scholar 

  4. Kantorovich, L.: On the transfer of masses. Dokl. Akad. Nauk. 37, 227–229 (1942)

    Google Scholar 

  5. Rachev, S., Rüschendorf, L.: Mass Transportation Problems: Theory, vol. 1. Springer, New York (1998)

    MATH  Google Scholar 

  6. Villani, C.: Topics in Optimal Transportation, vol. 58. AMS, Providence (2003)

    MATH  Google Scholar 

  7. Villani, C.: Optimal Transport: Old and New, vol. 338. Springer, New York (2008)

    MATH  Google Scholar 

  8. Gangbo, W., McCann, R.J.: The geometry of optimal transportation. Acta Math. 177(2), 113–161 (1996)

    Article  MathSciNet  MATH  Google Scholar 

  9. Jordan, R., Kinderlehrer, D., Otto, F.: The variational formulation of the Fokker–Planck equation. SIAM J. Math. Anal. 29, 1–17 (1998)

    Article  MathSciNet  MATH  Google Scholar 

  10. Benamou, J., Brenier, Y.: A computational fluid mechanics solution to the Monge–Kantorovich mass transfer problem. Numerische Mathematik 84(3), 375–393 (2000)

    Article  MathSciNet  MATH  Google Scholar 

  11. Ambrosio, L., Gigli, N., Savaré, G.: Gradient Flows in Metric Spaces and in the Space of Probability Measures. Birkhäuser Verlag, Basel (2008)

    MATH  Google Scholar 

  12. Ning, L., Georgiou, T.T., Tannenbaum, A.: Matrix-valued Monge–Kantorovich optimal mass transport. IEEE Trans. Autom. Control 60(2), 373–382 (2015)

    Article  MathSciNet  Google Scholar 

  13. Fortet, R.: Résolution d’un système d’equations de M. Schrödinger. J. Math. Pure Appl. 9, 83–105 (1940)

    MathSciNet  MATH  Google Scholar 

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

    Article  MathSciNet  MATH  Google Scholar 

  15. Jamison, B.: The Markov processes of Schrödinger. Z. Wahrscheinlichkeitstheorie verw. Gebiete 32, 323–331 (1975)

    Article  MathSciNet  MATH  Google Scholar 

  16. Föllmer, H.: Random fields and diffusion processes. In: Hennequin, P.L. (ed.) Ècole d’Ètè de Probabilitès de Saint-Flour XV–XVII, vol. 1362, pp. 102–203. Springer, New York (1988)

    Google Scholar 

  17. Wakolbinger, A.: Schrödinger bridges from 1931 to 1991. Contribuciones en probabilidad y estadistica matematica 3, 61–79 (1992)

    Google Scholar 

  18. Nelson, E.: Dynamical Theories of Brownian Motion. Princeton University Press, Princeton (1967)

    MATH  Google Scholar 

  19. Nelson, E.: Quantum Fluctuations. Princeton University Press, Princeton (1985)

    MATH  Google Scholar 

  20. Zambrini, J.C.: Stochastic mechanics according to E. Schrödinger. Phys. Rev. A 33(3), 1532–1548 (1986)

    Article  MathSciNet  Google Scholar 

  21. Zambrini, J.C.: Variational processes and stochastic versions of mechanics. J. Math. Phys. 27(9), 2307–2330 (1986)

    Article  MathSciNet  MATH  Google Scholar 

  22. Fenyes, I.: Eine wahrscheinlichkeitstheoretische Begründung und Interpretation der Quantenmechanik. Z. Physik 132, 81–106 (1952)

    Article  MathSciNet  MATH  Google Scholar 

  23. Bohm, D.: A suggested interpretation of the quantum theory in terms of “hidden” variables. Phys. Rev. 85, 166–179 (1952)

    Article  MathSciNet  MATH  Google Scholar 

  24. Bohm, D., Vigier, J.P.: Model of the causal interpretation of quantum theory in terms of a fluid with irregular fluctuations. Phys. Rev. 96, 208–216 (1954)

    Article  MathSciNet  MATH  Google Scholar 

  25. Levy, B.C., Krener, A.J.: Stochastic mechanics of reciprocal diffusions. J. Math. Phys. 37, 769 (1996)

    Article  MathSciNet  MATH  Google Scholar 

  26. Rosenbrock, H.H.: Doing quantum mechanics with control theory. IEEE Trans. Autom. Control 54, 73–77 (2000)

    Article  MathSciNet  MATH  Google Scholar 

  27. Dai Pra, P.: A stochastic control approach to reciprocal diffusion processes. Appl. Math. Optim. 23(1), 313–329 (1991)

    Article  MathSciNet  MATH  Google Scholar 

  28. Dai Pra, P., Pavon, M.: On the Markov processes of Schrödinger, the Feynman–Kac formula and stochastic control. In: Kaashoek, M.A., van Schuppen, J.H., Ran, A.C.M. (eds.) Realization and Modeling in System Theory, pp. 497–504. Birkhäuser, Boston (1990)

    Chapter  Google Scholar 

  29. Pavon, M., Wakolbinger, A.: On free energy, stochastic control, and Schrödinger processes. In: Di Masi, G.B., Gombani, A., Kurzhanski, A.A. (eds.) Modeling, Estimation and Control of Systems with Uncertainty, pp. 334–348. Birkhäuser, Boston (1991)

    Chapter  Google Scholar 

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

    Article  MATH  Google Scholar 

  31. Mikami, T., Thieullen, M.: Optimal transportation problem by stochastic optimal control. SIAM J. Control Optim. 47(3), 1127–1139 (2008)

    Article  MathSciNet  MATH  Google Scholar 

  32. Pavon, M., Ticozzi, F.: Discrete-time classical and quantum Markovian evolutions: maximum entropy problems on path space. J. Math. Phys. 51, 042104–042125 (2010)

    Article  MathSciNet  MATH  Google Scholar 

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

    Article  MathSciNet  MATH  Google Scholar 

  34. Georgiou, T.T., Pavon, M.: Positive contraction mappings for classical and quantum Schrödinger systems. J. Math. Phys. 56(033301), 1–24 (2015)

    MathSciNet  MATH  Google Scholar 

  35. Angenent, S., Haker, S., Tannenbaum, A.: Minimizing flows for the Monge–Kantorovich problem. SIAM J. Math. Anal. 35(1), 61–97 (2003)

    Article  MathSciNet  MATH  Google Scholar 

  36. Filliger, R., Hongler, M.O.: Relative entropy and efficiency measure for diffusion-mediated transport processes. J. Phys. A: Math. Gen. 38, 1247–1250 (2005)

    Article  MATH  Google Scholar 

  37. Filliger, R., Hongler, M.O., Streit, L.: Connection between an exactly solvable stochastic optimal control problem and a nonlinear reaction-diffusion equation. J. Optim. Theory Appl. 137, 497–505 (2008)

    Article  MathSciNet  MATH  Google Scholar 

  38. Chen, Y., Georgiou, T.T.: Stochastic bridges of linear systems. Preprint, http://arxiv.org/abs/1407.3421. IEEE Trans. Autom. Control (to appear)

  39. Chen, Y., Georgiou, T.T., Pavon, M.: Optimal steering of a linear stochastic system to a final probability distribution, Part I. preprint, http://arxiv.org/abs/1408.2222. IEEE Trans. Autom. Control (to appear)

  40. Chen, Y., Georgiou, T.T., Pavon, M.: Optimal steering of a linear stochastic system to a final probability distribution, Part II. Preprint, http://arxiv.org/abs/1410.3447. IEEE Trans. Autom. Control (to appear)

  41. Chen, Y., Georgiou, T.T., Pavon, M.: Optimal transport over a linear dynamical system. Preprint, http://arxiv.org/abs/1502.01265 (submitted for publication)

  42. Chen, Y., Georgiou, T.T., Pavon, M.: Entropic and displacement interpolation: a computational approach using the Hilbert metric. Preprint, http://arxiv.org/abs/1506.04255 (submitted for publication)

  43. Chen, Y., Georgiou, T.T., Pavon, M.: Fast cooling for a system of stochastic oscillators. Preprint, http://arxiv.org/abs/1411.1323v2 (submitted for publication)

  44. Mikami, T.: Monge’s problem with a quadratic cost by the zero-noise limit of h-path processes. Probab. Theory Relat. Fields 129, 245–260 (2004)

    Article  MathSciNet  MATH  Google Scholar 

  45. Mikami, T., Thieullen, M.: Duality theorem for the stochastic optimal control problem. Stoch. Proc. Appl. 116, 1815–1835 (2006)

    Article  MathSciNet  MATH  Google Scholar 

  46. Carlen, E.: Stochastic mechanics: a look back and a look ahead. In: Faris, W.G. (ed.) Diffusion, Quantum Theory and Radically Elementary Mathematics, vol. 47, pp. 117–139. Princeton University Press, Princeton (2006)

    Google Scholar 

  47. Kosmol, P., Pavon, M.: Lagrange Lemma and the optimal control of diffusions II: nonlinear Lagrange functionals. Syst. Control Lett. 24(3), 215–221 (1995)

    Article  MathSciNet  MATH  Google Scholar 

  48. Fleming, W.H., Soner, M.: Controlled Markov Processes and Viscosity Solutions, 2nd edn. Springer, New York (2006)

    MATH  Google Scholar 

  49. Tabak, E.G., Trigila, G.: Data-driven optimal transport. Commun. Pure. Appl. Math. doi:10.1002/cpa.21588 (2014)

  50. Karatzas, I., Shreve, S.E.: Brownian Motion and Stochastic Calculus. Springer, New York (1988)

    Book  MATH  Google Scholar 

  51. Föllmer, H.: Time Reversal on Wiener Space. Springer, New York (1986)

    MATH  Google Scholar 

  52. Dembo, A., Zeitouni, O.: Large Deviations Techniques and Applications, 2nd edn. Springer, New York (1998)

    Book  MATH  Google Scholar 

  53. Wakolbinger, A.: A simplified variational characterization of Schrödinger processes. J. Math. Phys. 30(12), 2943–2946 (1989)

    Article  MathSciNet  MATH  Google Scholar 

  54. Pavon, M.: Stochastic control and nonequilibrium thermodynamical systems. Appl. Math. Optim. 19, 187–202 (1989)

    Article  MathSciNet  MATH  Google Scholar 

  55. Fleming, W.H., Rishel, R.W.: Deterministic and Stochastic Optimal Control. Springer, Berlin (1975)

    Book  MATH  Google Scholar 

  56. Nagasawa, M.: Stochastic variational principle of Schrödinger Processes. In: Cinlar, E., Chung, K.L., Getoo, R.K., Fitzsimmons, P.J., Williams, R.J. (eds.) Seminar on Stochastic Processes, pp. 165–175. Birkhäuser, Boston (1989)

  57. Pavon, M.: Hamilton’s principle in stochastic mechanics. J. Math. Phys. 36, 6774–6800 (1995)

    Article  MathSciNet  MATH  Google Scholar 

  58. Madelung, E.: Quantentheorie in hydrodynamischer Form. Z. Physik 40, 322–326 (1926)

    Article  MATH  Google Scholar 

  59. Chen, Y., Georgiou, T.T., Pavon, M.: Optimal steering of inertial particles diffusing anisotropically with losses. In: Proceedings of the American Control Conference (2015)

Download references

Acknowledgments

Research partially supported by the NSF under Grant ECCS-1509387, the AFOSR under Grants FA9550-12-1-0319, and FA9550-15-1-0045 and by the University of Padova Research Project CPDA 140897. Part of the research of M.P. was conducted during a stay at the Courant Institute of Mathematical Sciences of the New York University whose hospitality is gratefully acknowledged.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Michele Pavon.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, Y., Georgiou, T.T. & Pavon, M. On the Relation Between Optimal Transport and Schrödinger Bridges: A Stochastic Control Viewpoint. J Optim Theory Appl 169, 671–691 (2016). https://doi.org/10.1007/s10957-015-0803-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10957-015-0803-z

Keywords

Mathematics Subject Classification

Navigation