Truncated Differentiation for Inverse Potential MFGs
Abstract
We study inverse potential mean-field games (MFGs), in which an unknown spatial inverse-cost (mobility) map is inferred from observed population densities. We solve the forward MFG with a preconditioned primal-dual hybrid gradient (PDHG) method and develop Jacobian-free backpropagation (JFB-), which records only the final iterations from a detached warm start while retaining the full forward solve. To analyze this truncated differentiation method, we show that the exact-proximal dual-extrapolated PDHG map is a metric resolvent of the maximal monotone KKT operator. This resolvent view shows that JFB- exactly differentiates a finite-trajectory surrogate and, under a locally fixed active set at an exact equilibrium detach point, converges to the implicit gradient as the tracked depth increases. Across several inverse-MFG settings, numerical experiments show that JFB-r at moderate tracked depths can achieve recovery accuracy comparable to full unrolling while reducing memory and runtime.
Cite
@article{arxiv.2608.00217,
title = {Truncated Differentiation for Inverse Potential MFGs},
author = {Siting Liu and Yat Tin Chow and Samy Wu Fung},
journal= {arXiv preprint arXiv:2608.00217},
year = {2026}
}