Entropic and displacement interpolation: a computational approach using the Hilbert metric
From MaRDI portal
Publication:3181069
Abstract: Monge-Kantorovich optimal mass transport (OMT) provides a blueprint for geometries in the space of positive densities -- it quantifies the cost of transporting a mass distribution into another. In particular, it provides natural options for interpolation of distributions (displacement interpolation) and for modeling flows. As such it has been the cornerstone of recent developments in physics, probability theory, image processing, time-series analysis, and several other fields. In spite of extensive work and theoretical developments, the computation of OMT for large scale problems has remained a challenging task. An alternative framework for interpolating distributions, rooted in statistical mechanics and large deviations, is that of Schroedinger bridges (entropic interpolation). This may be seen as a stochastic regularization of OMT and can be cast as the stochastic control problem of steering the probability density of the state-vector of a dynamical system between two marginals. In this approach, however, the actual computation of flows had hardly received any attention. In recent work on Schroedinger bridges for Markov chains and quantum evolutions, we noted that the solution can be efficiently obtained from the fixed-point of a map which is contractive in the Hilbert metric. Thus, the purpose of this paper is to show that a similar approach can be taken in the context of diffusion processes which i) leads to a new proof of a classical result on Schroedinger bridges and ii) provides an efficient computational scheme for both, Schroedinger bridges and OMT. We illustrate this new computational approach by obtaining interpolation of densities in representative examples such as interpolation of images.
Recommendations
- Stochastic control liaisons. Richard Sinkhorn meets Gaspard Monge on a Schrödinger bridge
- Computational optimal transport. With applications to data sciences
- An interpolating distance between optimal transport and Fisher-Rao metrics
- Entropic optimal transport: geometry and large deviations
- Convergence of entropic schemes for optimal transport and gradient flows
Cites work
- scientific article; zbMATH DE number 4199193 (Why is no real title available?)
- scientific article; zbMATH DE number 4138897 (Why is no real title available?)
- scientific article; zbMATH DE number 4080537 (Why is no real title available?)
- scientific article; zbMATH DE number 3001084 (Why is no real title available?)
- scientific article; zbMATH DE number 3005682 (Why is no real title available?)
- scientific article; zbMATH DE number 1909499 (Why is no real title available?)
- scientific article; zbMATH DE number 3238721 (Why is no real title available?)
- A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem
- A convexity principle for interacting gases
- A simplified variational characterization of Schrödinger processes
- A smoothed dual approach for variational Wasserstein problems
- A stochastic control approach to reciprocal diffusion processes
- A survey of the Schrödinger problem and some of its connections with optimal transport
- An automorphism of product measures
- Constructing optimal maps for Monge's transport problem as a limit of strictly convex costs
- Controllability of a Fokker-Planck equation, the Schrödinger system, and a related stochastic optimal control (revised version)
- Extensions of Jentzsch's Theorem
- Fast cooling for a system of stochastic oscillators
- From the Schrödinger problem to the Monge-Kantorovich problem
- Geometric Methods for Spectral Analysis
- Gradient flows in metric spaces and in the space of probability measures
- Hilbert's metric and positive contraction mappings in a Banach space
- Iterative Bregman projections for regularized transportation problems
- Large deviations techniques and applications.
- Mass transportation problems. Vol. 1: Theory. Vol. 2: Applications
- Measure theory. Vol. I and II
- Minimizing Flows for the Monge--Kantorovich Problem
- Monge's problem with a quadratic cost by the zero-noise limit of \(h\)-path processes
- Nonlinear Perron-Frobenius theory
- On the Projective Contraction Ratio for Positive Linear Mappings
- On the relation between optimal transport and Schrödinger bridges: a stochastic control viewpoint
- Optimal Steering of a Linear Stochastic System to a Final Probability Distribution, Part I
- Optimal Steering of a Linear Stochastic System to a Final Probability Distribution, Part II
- Optimal Transport
- Optimal Transport Over a Linear Dynamical System
- Optimal Transportation Problem by Stochastic Optimal Control
- Optimal mass transport for registration and warping
- Positive contraction mappings for classical and quantum Schrödinger systems
- Reciprocal processes
- Relative entropy and efficiency measure for diffusion-mediated transport processes
- The Variational Formulation of the Fokker--Planck Equation
- The geometry of optimal transportation
Cited in
(27)- Regularity of Schrödinger's functional equation in the weak topology and moment measures
- Multimarginal Optimal Transport with a Tree-Structured Cost and the Schrödinger Bridge Problem
- On the linear convergence of the multimarginal Sinkhorn algorithm
- Steering the distribution of agents in mean-field games system
- Regularity of Schrödinger's functional equation and mean field PDEs for h-path processes
- A non-commutative entropic optimal transport approach to quantum composite systems at positive temperature
- Fast and asymptotic steering to a steady state for networks flows
- Generalized Sinkhorn iterations for regularizing inverse problems using optimal mass transport
- Vector and matrix optimal mass transport: theory, algorithm, and applications
- Extremal flows in Wasserstein space
- Fast cooling for a system of stochastic oscillators
- Data assimilation: the Schrödinger perspective
- A proof of the Caffarelli contraction theorem via entropic regularization
- Quantitative stability of regularized optimal transport and convergence of Sinkhorn's algorithm
- An efficient algorithm for matrix-valued and vector-valued optimal mass transport
- Diffusion Schrödinger bridges for Bayesian computation
- An optimal transport approach for the Schrödinger bridge problem and convergence of Sinkhorn algorithm
- Stochastic control liaisons. Richard Sinkhorn meets Gaspard Monge on a Schrödinger bridge
- Wasserstein geometry of quantum states and optimal transport of matrix-valued measures
- Computations of optimal transport distance with Fisher information regularization
- Entropic regularization of continuous optimal transport problems
- Quantitative uniform stability of the iterative proportional fitting procedure
- On the relation between optimal transport and Schrödinger bridges: a stochastic control viewpoint
- A differential approach to the multi-marginal Schrödinger system
- Traversing the Schrödinger bridge strait: Robert Fortet's marvelous proof redux
- Probabilistic Lambert problem: connections with optimal mass transport, Schrödinger bridge, and reaction-diffusion PDEs
- The Most Likely Evolution of Diffusing and Vanishing Particles: Schrödinger Bridges with Unbalanced Marginals
This page was built for publication: Entropic and displacement interpolation: a computational approach using the Hilbert metric
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3181069)
