Saved in:
Bibliographic Details
Main Authors: Li, Ming, Gao, Ting, Dua, Jingqiao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.18035
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912973514080256
author Li, Ming
Gao, Ting
Dua, Jingqiao
author_facet Li, Ming
Gao, Ting
Dua, Jingqiao
contents Controlling the high-dimensional neural dynamics during epileptic seizures remains a significant challenge due to the nonlinear characteristics and complex connectivity of the brain. In this paper, we propose a novel framework, namely Graph-Regularized Koopman Mean-Field Game (GK-MFG), which integrates Reservoir Computing (RC) for Koopman operator approximation with Alternating Population and Agent Control Network (APAC-Net) for solving distributional control problems. By embedding Electroencephalogram (EEG) dynamics into a linear latent space and imposing graph Laplacian constraints derived from the Phase Locking Value (PLV), our method achieves robust seizure suppression while respecting the functional topological structure of the brain.
format Preprint
id arxiv_https___arxiv_org_abs_2603_18035
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Taming Epilepsy: Mean Field Control of Whole-Brain Dynamics
Li, Ming
Gao, Ting
Dua, Jingqiao
Machine Learning
Controlling the high-dimensional neural dynamics during epileptic seizures remains a significant challenge due to the nonlinear characteristics and complex connectivity of the brain. In this paper, we propose a novel framework, namely Graph-Regularized Koopman Mean-Field Game (GK-MFG), which integrates Reservoir Computing (RC) for Koopman operator approximation with Alternating Population and Agent Control Network (APAC-Net) for solving distributional control problems. By embedding Electroencephalogram (EEG) dynamics into a linear latent space and imposing graph Laplacian constraints derived from the Phase Locking Value (PLV), our method achieves robust seizure suppression while respecting the functional topological structure of the brain.
title Taming Epilepsy: Mean Field Control of Whole-Brain Dynamics
topic Machine Learning
url https://arxiv.org/abs/2603.18035