On the Equivalence of Stochastic Control and Path Space Formulations for Schrödinger Bridges over Compact Connected Lie Groups
Abstract
We establish the equivalence between the stochastic optimal control and path space formulations of the Schrödinger bridge problem (SBP) for the kinematic equation on a compact connected Lie group. Using the geometric concepts of horizontal lift and stochastic anti-development, we derive a Girsanov-type change-of-measure result, and show that the expected control energy equals the relative entropy of the controlled path law with respect to the reference Wiener measure. Thus, the SBP is equivalently a path space relative entropy minimization problem subject to prescribed endpoint marginals.Our result has three useful implications. From an analytic viewpoint, the shown equivalence helps prove the existence and uniqueness of the SB. From a probabilistic viewpoint, it helps interpret the SB as the most probable deviation of the uncontrolled stochastic dynamics consistent with the endpoint constraints. From a computational viewpoint, it allows using static Sinkhorn recursions to directly solve the relative entropy minimization problem and compute the optimal path measure. We illustrate the equivalence numerically on the torus 𝕋2. The code is publicly available at: https://github.com/gradslab/LargeDeviationSBP
Related
- Well-Posedness of Stochastic Mean-Field Schrödinger Porous-Medium Equations and Control of Their Modal Reductions
- Degree-list Kempe equivalence for 3-connected graphs
- Global Energy Solutions for Normalized Linear Stochastic Schrödinger Equations
- Stochastic Homogenization of Schrödinger Equations with Exponentially Mixing Sub-Gaussian Potentials
- Model Predictive Control of Wind Turbines: A Model-Oriented Review of Prediction Models, Control Objectives, and Nonlinear Aerodynamic Formulations
BibTeX
@misc{mahmood2026equivalence,
title = {{On the Equivalence of Stochastic Control and Path Space Formulations for Schrödinger Bridges over Compact Connected Lie Groups}},
author = {Hamza Mahmood and Georgiy A. Bondar and Abhishek Halder and Adeel Akhtar},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.13758},
eprint = {2609.13758},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.13758},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - On the Equivalence of Stochastic Control and Path Space Formulations for Schrödinger Bridges over Compact Connected Lie Groups
AU - Hamza Mahmood
AU - Georgiy A. Bondar
AU - Abhishek Halder
AU - Adeel Akhtar
PY - 2026
DA - 2026/09/12
PB - arXiv
DO - 10.48550/arxiv.2609.13758
UR - https://arxiv.org/abs/2609.13758
AB - We establish the equivalence between the stochastic optimal control and path space formulations of the Schrödinger bridge problem (SBP) for the kinematic equation on a compact connected Lie group. Using the geometric concepts of horizontal lift and stochastic anti-development, we derive a Girsanov-type change-of-measure result, and show that the expected control energy equals the relative entropy of the controlled path law with respect to the reference Wiener measure. Thus, the SBP is equivalently a path space relative entropy minimization problem subject to prescribed endpoint marginals.Our result has three useful implications. From an analytic viewpoint, the shown equivalence helps prove the existence and uniqueness of the SB. From a probabilistic viewpoint, it helps interpret the SB as the most probable deviation of the uncontrolled stochastic dynamics consistent with the endpoint constraints. From a computational viewpoint, it allows using static Sinkhorn recursions to directly solve the relative entropy minimization problem and compute the optimal path measure. We illustrate the equivalence numerically on the torus 𝕋^2. The code is publicly available at: https://github.com/gradslab/LargeDeviationSBP
ER -