Abstract
In this article we investigate entropic interpolations. These measure valued curves describe the optimal solutions of the Schrödinger problem Schrödinger (Sitzungsberichte Preuss Akad. Wiss. Berlin. Phys. Math. 144:144–153 1931), which is the problem of finding the most likely evolution of a system of independent Brownian particles conditionally to observations. It is well known that in the short time limit entropic interpolations converge to the McCann-geodesics of optimal transport. Here we focus on the long-time behaviour, proving in particular asymptotic results for the entropic cost and establishing the convergence of entropic interpolations towards the heat equation, which is the gradient flow of the entropy according to the Otto calculus interpretation. Explicit rates are also given assuming the Bakry-Émery curvature-dimension condition. In this respect, one of the main novelties of our work is that we are able to control the long time behavior of entropic interpolations assuming the CD(0,n) condition only.
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, 2nd edn. Birkhäuser, Basel (2008)
Benamou, J.-D., Brenier, Y.: A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem. Numer. Math. 84(3), 375–393 (2000)
Bakry, D., Emery, M.: Diffusions hypercontractives. Sémin de probabilités XIX, Univ. Strasbourg 1983/84. Proc. Lect Notes Math. 1123, 177–206 (1985)
Bakry, D., Gentil, I., Ledoux, M.: Analysis and geometry of Markov diffusion operators. Springer, Cham (2014)
Bakry, D., Ledoux, M.: A logarithmic Sobolev form of the Li-Yau parabolic inequality. Rev. Mat Iberoam. 22(2), 683–702 (2006)
Braides, A.: Γ-convergence for beginners, vol. 22. Oxford University Press, Oxford (2002)
Backhoff-Veraguas, J., Conforti, G., Gentil, I., Léonard, C.: The mean field schrödinger problem: ergodic behavior, entropy estimates and functional inequalities. Probab. Theory Related Fields 178(1-2), 475–530 (2020)
Clerc, G., Conforti, G., Gentil, I.: On the variational interpretation of local logarithmic sobolev inequalities, To appear in Ann. Fac. Sci. Toulouse (2020)
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(2), 671–691 (2016)
Clerc, G.: Regularity of the schrödinger cost Preprint (2021)
Conforti, G.: A second order equation for Schrödinger bridges with applications to the hot gas experiment and entropic transportation cost. Probab. Theory Relat. Fields 174(1-2), 1–47 (2019)
Costa, M.H.M.: A new entropy power inequality. IEEE Trans. Inf. Theory 31, 751–760 (1985)
Conforti, G., Tamanini, L.: A formula for the time derivative of the entropic cost and applications. J. Funct. Anal. 280(11), 48 (2021)
Dal Maso, G.: An introduction to Γ-convergence, vol. 8. Springer Science & Business Media, Berlin (2012)
Erbar, M., Kuwada, K., Sturm, K.-T.: On the equivalence of the entropic curvature-dimension condition and Bochner’s inequality on metric measure spaces. Invent. Math. 201(3), 993–1071 (2015)
Erbar, M.: The heat equation on manifolds as a gradient flow in the Wasserstein space. Ann. Inst. Henri Poincaré, Probab. Stat. 46(1), 1–23 (2010)
Follmer, H.: Random fields and diffusion processes. Calcul des probabilités, Éc. d’Été, Saint-Flour. 1985-87. Lect. Notes Math. 1362, 101–203 (1988)
Feydy, J., Séjourné, T., Vialard, F.-X., Amari, S.-I., Trouvé, A., Peyré, G.: Interpolating between optimal transport and mmd using sinkhorn divergences. In: The 22nd International Conference on Artificial Intelligence and Statistics, pp 2681–2690 (2019)
Gigli, N.: Second order analysis on \((\mathcal {P}_{2}(M), W_{2})\). Mem. Am. Math Soc. 1018, 154 (2012)
Gentil, I., Léonard, C., Ripani, L.: About the analogy between optimal transport and minimal entropy. Ann. Fac. Sci. Toulouse Math. (6) 26(3), 569–601 (2017)
Gentil, I., Léonard, C., Ripani, L.: Dynamical aspects of the generalized Schrö,dinger problem via Otto calculus – a heuristic point of view. Rev. Mat Iberoam. 36(4), 1071–1112 (2020)
Gigli, N., Tamanini, L.: Benamou-Brenier and Kantorovich duality formulas for the entropic cost on RCD∗(K,N) spaces. Probab Theory Relat. Fields 176(1-2), 1–34 (2020)
Gigli, N., Tamanini, L.: Second order differentiation formula on RCD*(K,N), spaces. J. Eur. Math Soc. (JEMS) 23(5), 1727–1795 (2021)
Jordan, R., Kinderlehrer, D., Otto, F.: The variational formulation of the Fokker-Planck equation. SIAM J. Math. Anal. 29(1), 1–17 (1998)
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)
LaFrance, J.T., Barney, L.D.: The envelope theorem in dynamic optimization. Journal of Economic Dynamics and Control 15(2), 355–385 (1991)
McKenzie, L.: Turnpike theorems for a generalized Leontief model. Econometrica (pre-1986) 31(1, 2), 165 (1963)
Mikami, T.: Monge’s problem with a quadratic cost by the zero-noise limit of h-path processes. Probab. Theory Relat. Fields 129(2), 245–260 (2004)
Otto, F.: The geometry of dissipative evolution equations: The porous medium equation. Commun. Partial Differ. Equations 26(1-2), 101–174 (2001)
Otto, F., Villani, C.: Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality. J. Funct. Anal. 173(2), 361–400 (2000)
Peyré, G., Cuturi, M.: Computational optimal transport. Foundations and Trends in Machine Learning 11(5-6), 355–607 (2019)
Ripani, L.: Convexity and regularity properties for entropic interpolations. J. Funct Anal. 277(2), 368–391 (2019)
Schrödinger, E.: ÜBer die Umkehrung der Naturgesetze. Sitzungsberichte Preuss Akad. Wiss. Berlin. Phys. Math. 144, 144–153 (1931)
Schrödinger, E.: Sur la théorie relativiste de l’électron et l’interprétation de la mécanique quantique. Ann. Inst. H. Poincaré, 2, 269–310 (1932)
Tamanini, L.: Analysis and geometry of RCD spaces via the schrödinger problem Phd Thesis (2017)
Trélat, E., Zuazua, E.: The turnpike property in finite-dimensional nonlinear optimal control. Journal of Differential Equations 258(1), 81–114 (2015)
Villani, C.: Optimal transport. Old and New. Springer, Berlin (2009)
von Renesse, M.-K., Sturm, K.-T.: Transport inequalities, gradient estimates, entropy and Ricci curvature. Commun. Pure Appl. Math. 58(7), 923–940 (2005)
Acknowledgements
This research was supported by the French ANR-17-CE40-0030 EFI project. We would also like to warmly thank the referee who gave us useful comments and pointed out references.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix : A: Details About the Examples
Appendix : A: Details About the Examples
1.1 A.1 A (0,n)-convex Function
To understand what happened in the (0,n)-convex case, let’s begin by an example on the real line. The prototypal (0,1)-convex function is \(F(x)=-\log x\), x > 0. This is a (0,1)-convex function since \( F^{\prime \prime }=(F^{\prime })^2. \) Let x,T > 0, for simplicity we just treat the case where x = y. The gradient flow from x > 0, denoted by (St(x))t≥ 0 is the solution of the ODE \(\dot X_t={1}/{X_t}\) starting from x, hence for all t > 0, \(S_t(x)=\sqrt {2t+x^2}\).
The Newton system associated is
Now \((X_t^T)_{t \in [0,T]}\) denote the entropic interpolation between x and x. The conserved quantity is given by \( E_{T}(x,x)=\dot {X_t^T}^2-\frac {1}{{X_t^T}^2}. \) Thus \(\left |\dot X_t^T\right |=\sqrt {E_{T}(x,x)+F^{\prime }(X_t^T)^2}\) and we can deduce that
In this example we have enough information to compute explicitly the conserved quantity.
Proposition A.1
For T > 0 and x ∈R, \( E_{T}(x,x)= 2\frac {-x^2- \sqrt {x^4+T^2}}{T^2}. \)
Proof
By the continuity in T/2 of \(\left (X_t^T \right )_{t \in [0,T ]}\) we can deduce that \(E_{T}(x,x)=-F^{\prime }(X_{T/2}^T)^2\). Notice that for all t ∈ [0,T/2]
and
By integration of this inequality we see that for every t ∈ [0,T/2)
When t = T/2 we get \( \frac {T^2}{4}E_{T}(x,x)^2- \frac {E_{T}(x,x)}{F^{\prime }(x)^2}-1=0 \) and since ET(x,x) ≤ 0 we deduce that
□
Hence ET(x,x) is of order 1/T in this case. From Eq. 1, we can deduce an explicit formula for \(X_t^T\).
Proposition A.2
For x ∈R and T > 0, the entropic interpolation from x to x is given by
Furthermore \(X_t^T \rightarrow S_t(x)\) when \(T \rightarrow \infty \), more precisely
hence there exists a constant C > 0 such that \( |X_t^T-S_t(x)| \underset {T \rightarrow \infty }{\sim } \frac {C}{T}. \)
In this particular case we can compute the cost in an explicit way.
Proposition A.3
For every x ∈R, \( C_{T}(x,x) \underset {T \rightarrow \infty }{\sim } 2 \log (T). \)
Proof
By the very defnition of the cost,
Hence, \( C_{T}(x,x) \underset {T \rightarrow \infty }{\sim } 2 \log (T). \)□
1.2 A.2 The Example of two Gaussians on R
This example take place on R. This is a flat space of dimension one, that mean it verify the CD(0, 1) condition. Recall that for m ∈R and σ > 0 the normal law of expected value m and variance σ2 is the probability measure on R with density against the Lebesgue measure,
In this case we know an expression for the heat semigroup, for f ∈ L∞(R), we have
Furthermore, for all m ∈R and σ,t > 0 we know that from elementary probability theory
Thanks to all of these considerations we can make explicit calculus in this case. For simplicity here we are gonna consider the case of two centered gaussian measure, that is σ2 = 1. Let x0,x1 ∈R, T > 0, \(\mu =\mathcal {N}(x_{0},1)\) and \(\nu = \mathcal {N}(x_1,1)\). We can solve explicitely the Schrödinger system
by searching solutions of the form \(x \mapsto a \exp \left (- \frac {(x-b)^2}{2c^2} \right )\) with a,b,c ∈R. We can make explicit computations to find two solutions given by for all x ∈R
where the parameter \(\mathcal {D}_{T}\) is given by \( \mathcal {D}_{T}^2=\sqrt {(T-1)^2+2T}-(T-1). \) Observe that f is the density of the normal law \(\mathcal {N}\left (\frac {\mathcal {D}_{T}^2(\mathcal {D}_{T}^2+2T)^2}{(\mathcal {D}_{T}^2+2T)^2-\mathcal {D}_{T}^2} \left (x_{0}-\frac {\mathcal {D}_{T}^2}{\mathcal {D}_{T}^2+2T}x_1 \right ),\mathcal {D}_{T}^2 \right )\). This is an arbitrary choice, because there is only unicity up to the trivial transform (f,g)↦(cf,g/c) for some c ∈R. From those expressions we can easily deduce a formula for the entropic interpolation \((\mu _t^T)_{t \in [0,T]}\) between μ and ν, actually it’s a normal law \(\mathcal {N}(x_t^T,\sigma _t^T)\) where the parameter are given by
We want to quantify the convergence of μT toward the gradient flow \(\left (P_t^{*} (\mu ) \right )_{t \in [0,T]}\). The gradient flow is given by \(P_t^{*}(\mu )=P_t\left (\frac {d\mu }{dm} \right )dm=\mathcal {N}(x_{0},\mathcal {D}_{T}^2+2t)\). Actually the Wasserstein distance between two gaussian measures can be explicitely computed. Indeed let \(\mu = \mathcal {N}(m_{0},\sigma _{0}^2)\) and \(\nu =\mathcal {N}(m_1,\sigma _1^2)\), the map \(T:x \mapsto \frac {\sigma _1}{\sigma _{0}}(x-m_{0})+m_1\) verify T#μ = ν, hence by Brenier theorem \(W_2^2(\mu ,\nu )={\int \limits } |x-T(x)|^2 d \mu (x)\). From this expression and some easy computations we find
For the detail and the extension to Gaussian vectors we refer to [31, Remark 2.31]. Hence we can compute explicitly the Wasserstein distance between the entropic interpolation and the gradient flow.
Proposition A.4
In the notations of this subsection
and there exists a constant C > 0 such that \( W_2^2(\mu _t^T,P_t^{*} \mu ) \underset {T \rightarrow \infty }{\sim } \frac {C}{T^2}. \)
The velocity of \(\left (\mu _t^T \right )_{t \in [0,T]}\) is given by
Now we have all the element we need to compute the conserved quantity, and the following proposition follow from basic integration.
Proposition A.5
In the notations of this subsection we have the following equality for every T > 0,
In particular we can take t = T/2 to find, \( \mathcal {E}_{T}(\mu ,\nu ) \underset {T \rightarrow \infty }{\sim }\frac {(x_1-x_{0})^2}{T^2}-\frac {2}{T+2} \) and finally we get
Rights and permissions
About this article
Cite this article
Clerc, G., Conforti, G. & Gentil, I. Long-time Behaviour of Entropic Interpolations. Potential Anal 59, 65–95 (2023). https://doi.org/10.1007/s11118-021-09961-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11118-021-09961-w