Second-Order Mean-Field Schrödinger Bridges with Partial State Information
Abstract
Motivated by scenarios in control systems where decision making is informed by only partial information about the states, we introduce a novel formulation of the Schrödinger bridge problem for inertial interacting-agent systems. Within our setting, the agent ensemble is steered to match partial specifications of the collective configuration. Our analysis pertains to a mean-field framework in which the collective dynamics are described by a nonlinear Vlasov--Fokker--Planck integro-PDE with nonlocal interactions. We assume that only distributions over positions are specified at the endpoints of a finite time horizon, representing aggregate population snapshots, while the corresponding velocity degrees of freedom remain unspecified. We derive the associated optimality system, identifying the optimal controlled evolution as jointly informed by the initial and terminal specifications through forward and backward propagation in time. We also show that the partial endpoint specifications bring about distinct conditions on the optimal control and the consistent evolution. Subsequently, to compute solutions to the optimality system, we develop a nested fixed-point algorithm inspired by the classical Fortet--Sinkhorn iteration, but extended to handle the nonlinearities arising from nonlocal interactions and temporal coupling.
Related
- Mutual Information Optimal Density Control of Linear Systems and Generalized Schrödinger Bridges with Reference Refinement
- Second-order fields for stochastic partial differential equations
- Beyond Second-Order Information: Paid Logistic Regression with Noisy Features
- Quantum-Enhanced Sampling of Schrödinger Bridges
- Kinetic Mean-Field Planning via Schrödinger Bridges: Existence, Penalization, and Consistency Bounds
BibTeX
@misc{eldesoukey2026secondorder,
title = {{Second-Order Mean-Field Schrödinger Bridges with Partial State Information}},
author = {Asmaa Eldesoukey and Md Zulfiqur Haider and Italo Napolitano and Yongxin Chen and Abhishek Halder},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.02537},
eprint = {2610.02537},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.02537},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Second-Order Mean-Field Schrödinger Bridges with Partial State Information
AU - Asmaa Eldesoukey
AU - Md Zulfiqur Haider
AU - Italo Napolitano
AU - Yongxin Chen
AU - Abhishek Halder
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.02537
UR - https://arxiv.org/abs/2610.02537
AB - Motivated by scenarios in control systems where decision making is informed by only partial information about the states, we introduce a novel formulation of the Schrödinger bridge problem for inertial interacting-agent systems. Within our setting, the agent ensemble is steered to match partial specifications of the collective configuration. Our analysis pertains to a mean-field framework in which the collective dynamics are described by a nonlinear Vlasov--Fokker--Planck integro-PDE with nonlocal interactions. We assume that only distributions over positions are specified at the endpoints of a finite time horizon, representing aggregate population snapshots, while the corresponding velocity degrees of freedom remain unspecified. We derive the associated optimality system, identifying the optimal controlled evolution as jointly informed by the initial and terminal specifications through forward and backward propagation in time. We also show that the partial endpoint specifications bring about distinct conditions on the optimal control and the consistent evolution. Subsequently, to compute solutions to the optimality system, we develop a nested fixed-point algorithm inspired by the classical Fortet--Sinkhorn iteration, but extended to handle the nonlinearities arising from nonlocal interactions and temporal coupling.
ER -