Kinetic Mean-Field Planning via Schrödinger Bridges: Existence, Penalization, and Consistency Bounds
Abstract
We study a mean-field planning problem for a swarm of interacting, non-cooperative agents whose dynamics are stochastic and kinetic. The noise acts on the velocity only, and the interaction (of Cucker-Smale type for instance) enters through the drift. For a fixed flow, the problem reduces to a Schrödinger bridge problem, and we first prove the existence of an equilibrium by a Schauder fixed-point argument. Then we replace the hard terminal constraint by a penalty function and show that equilibria of the penalized problems converge, along subsequences, to an equilibrium of the original problem. Since equilibria are not unique in general, we instead quantify the consistency error, which measures how far an equilibrium of the penalized problem is from being an equilibrium of the original one. The rate is of order n−1/2 for the relative-entropy penalty. The proof relies on the quantitative stability of entropic optimal transport and on a pointwise linear growth bound on the score of the degenerate reference dynamics, which is of independent interest.
Related
- Serrin-type overdetermination in scaling limits: Sharp existence and asymptotic behavior of quasi-linear Schrödinger energy ground states
- Existence and consistency of weighted maximum likelihood estimator for extreme quantile regression
- A quasi-linear Schrödinger equation for nucleons : existence, uniqueness and asymptotic behavior
- Global existence of the s-Schrödinger maps in n ≥ 5
- Existence of multi-solitons for logarithmic Schrödinger equation with a perturbation of a smooth L2-subcritical function nonlinearity
BibTeX
@misc{bayraktar2026kinetic,
title = {{Kinetic Mean-Field Planning via Schrödinger Bridges: Existence, Penalization, and Consistency Bounds}},
author = {Erhan Bayraktar and Zhiyan Ding and Hiroaki Horikawa},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.28924},
eprint = {2610.28924},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.28924},
}
RIS
TY - UNPB
TI - Kinetic Mean-Field Planning via Schrödinger Bridges: Existence, Penalization, and Consistency Bounds
AU - Erhan Bayraktar
AU - Zhiyan Ding
AU - Hiroaki Horikawa
PY - 2026
DA - 2026/10/20
PB - arXiv
DO - 10.48550/arxiv.2610.28924
UR - https://arxiv.org/abs/2610.28924
AB - We study a mean-field planning problem for a swarm of interacting, non-cooperative agents whose dynamics are stochastic and kinetic. The noise acts on the velocity only, and the interaction (of Cucker-Smale type for instance) enters through the drift. For a fixed flow, the problem reduces to a Schrödinger bridge problem, and we first prove the existence of an equilibrium by a Schauder fixed-point argument. Then we replace the hard terminal constraint by a penalty function and show that equilibria of the penalized problems converge, along subsequences, to an equilibrium of the original problem. Since equilibria are not unique in general, we instead quantify the consistency error, which measures how far an equilibrium of the penalized problem is from being an equilibrium of the original one. The rate is of order n^−1/2 for the relative-entropy penalty. The proof relies on the quantitative stability of entropic optimal transport and on a pointwise linear growth bound on the score of the degenerate reference dynamics, which is of independent interest.
ER -