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

• Published in: Journal of optimization theory and applications Vol. 169; no. 2; pp. 671 - 691
• Main Authors: Chen, Yongxin, Georgiou, Tryphon T., Pavon, Michele
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.05.2016; Springer Nature B.V
• Subjects: Applications of Mathematics; Calculus of Variations and Optimal Control; Optimization; Computational fluid dynamics; Differential equations; Engineering; Joints; Mathematical analysis; Mathematics; Mathematics and Statistics; Noise; Operations Research/Decision Theory; Optimal control; Optimization; Partial differential equations; Quantum physics; Schroedinger equation; Stochastic control theory; Stochastic processes; Studies; Theory of Computation; Transport; Schrödinger bridge; 49L20; 49J20; 60J60; 35Q35; Stochastic control; Optimal transport; 28A50
• ISSN: 0022-3239; 1573-2878
• DOI: 10.1007/s10957-015-0803-z

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.