We consider the problem to identify the most likely flow in phase space, of (inertial) particles under stochastic forcing, that is in agreement with spatial (marginal) distributions that are specified at a set of points in time. The question raised generalizes the classical Schrodinger Bridge Problem (SBP) which seeks to interpolate two specified end-point marginal distributions of overdamped particles driven by stochastic excitation. While we restrict our analysis to second-order dynamics for the particles, the data represents partial (i.e., only positional) information on the flow at {\em multiple} time-points. The solution sought, as in SBP, represents a probability law on the space of paths this closest to a uniform prior while consistent with the given marginals. We approach this problem as an optimal control problem to minimize an action integral a la Benamou-Brenier, and derive a time-symmetric formulation that includes a Fisher information term on the velocity field. We underscore the relation of our problem to recent measure-valued splines in Wasserstein space, which is akin to that between SBP and Optimal Mass Transport (OMT). The connection between the two provides a Sinkhorn-like approach to computing measure-valued splines. We envision that interpolation between measures as sought herein will have a wide range of applications in signal/images processing as well as in data science in cases where data have a temporal dimension.
Nonlocal Onsager Operators and Entropy Dissipation for Finite-State Schrödinger Bridges
Higher Institute of Computer Science and Multimedia of Sfax, University of Sfax(萨法克斯多媒体与计算机科学高等学院,萨法克斯大学);Qassim University(卡西姆大学);Sfax Preparatory Engineering Institute, University of Sfax(萨法克斯预备工程学院,萨法克斯大学)
Schrödinger Bridge Over A Compact Connected Lie Group
Department of Mechanical & Industrial Engineering(机械与工业工程系);New Jersey Institute of Technology(新泽西理工学院);Department of Aerospace Engineering(航空航天工程系);Iowa State University(爱荷华州立大学)
Nonlinear Non-Gaussian Density Steering with Input and Noise Channel Mismatch: Sinkhorn with Memory for Solving the Control-affine Schrödinger Bridge Problem
Department of Applied Mathematics, University of California Santa Cruz(加州大学圣克鲁兹分校应用数学系);Department of Aerospace Engineering, Iowa State University(爱荷华州立大学航空航天工程系);School of Aerospace Engineering, Georgia Institute of Technology(佐治亚理工学院航空航天工程学院)
A Generalized Sinkhorn Algorithm for Mean-Field Schrödinger Bridge
Department of Aerospace Engineering, Iowa State University(爱荷华州立大学航空航天工程系);School of Aerospace Engineering, Georgia Institute of Technology(佐治亚理工学院航空航天工程学院)
Schrödinger bridge for generative AI: Soft-constrained formulation and convergence analysis
Department of Mathematics, University of Southern California(美国南加州大学数学系);Department of Statistics and Applied Probability, University of California(加州大学圣塔芭芭拉分校统计与应用概率系);Department of Management of Science & Engineering, Stanford University(斯坦福大学科学与工程管理系)
Optimal Multimarginal Schrödinger Bridge: Minimum Spanning Tree over Measure-valued Vertices
Department of Applied Mathematics, University of California Santa Cruz(应用数学系,加州大学圣克鲁兹分校);Department of Aerospace Engineering, Iowa State University(航空航天工程系,爱荷华州立大学)
Stochastic Learning of Computational Resource Usage as Graph Structured Multimarginal Schrödinger Bridge
Department of Applied Mathematics, University of California, Santa Cruz(应用数学系,加州大学圣克鲁兹分校);Department of Computer and Information Science, University of Pennsylvania(计算机与信息科学系,宾夕法尼亚大学);Department of Aerospace Engineering, Iowa State University(航空航天工程系,爱荷华州立大学)