Truncated Differentiation for Inverse Potential MFGs

DOI10.48550/arXiv.2608.00217MaRDI QIDQ7284575arXivFDO

Authors Siting Liu, Yat Tin Chow, Samy Wu Fung

Publication date 31 July 2026

Published in arXiv

Tldr We study inverse potential mean-field games (MFGs) by solving forward MFG with a preconditioned primal-dual hybrid gradient method and develop Jacobian-free backpropagation, which records only the final r iterations from a detached warm start while retaining the full forward solve. JFB-r converges to the implicit gradient as the tracked depth increases under a locally fixed active set at an exact equilibrium detach point.

Full work available at URL https://doi.org/10.48550/arXiv.2608.00217

Mathematics Subject Classification ID

Mean field games and control (49N80)

arXiv classification

math.NAmath.OC

Cites work

• A Bilevel Optimization Method for Inverse Mean-Field Games
• A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem
• A Machine Learning Framework for Solving High-Dimensional Mean Field Game and Mean Field Control Problems
• A mean field game inverse problem
• A Neural Network Approach Applied to Multi-Agent Optimal Control
• A Neural Network Approach Applied to Multi-Agent Optimal Control
• A Neural Network Approach for High-Dimensional Optimal Control Applied to Multi-Agent Path Finding
• A Neural Network Approach for High-Dimensional Optimal Control Applied to Multi-Agent Path Finding
• A numerical algorithm for inverse problem from partial boundary measurement arising from mean field game problem
• A policy iteration method for inverse mean field games
• A splitting algorithm for dual monotone inclusions involving cocoercive operators
• Alternating the Population and Control Neural Networks to Solve High-Dimensional Stochastic Mean-Field Games
• Augmented Lagrangian methods for transport optimization, mean field games and degenerate elliptic equations
• Computational methods for first-order nonlocal mean field games with applications
• Convergence analysis of primal-dual algorithms for a saddle-point problem: from contraction perspective
• Convex analysis and monotone operator theory in Hilbert spaces
• Decoding Mean Field Games from Population and Environment Observations By Gaussian Processes
• Equilibrium correction iteration for a class of mean-field game inverse problems
• Explainable AI via Learning to Optimize
• Feasibility-based fixed point networks
• Implicit Deep Learning
• Inverse optimal transport
• Inverse problems for mean field games
• Joint Inference of Trajectory and Obstacle in Mean-Field Games via Bilevel Optimization
• Kernel Expansions for High-Dimensional Mean-Field Control with Non-local Interactions
• Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
• Learning surrogate potential mean field games via Gaussian processes: a data-driven approach to ill-posed inverse problems
• Lipschitz stability for determination of states and inverse source problem for the mean field game equations
• Mean field games
• Mean field games and applications: numerical aspects
• Mean field games: numerical methods
• Mean field games: numerical methods for the planning problem
• Monotone (nonlinear) operators in Hilbert space
• Monotone Operators and the Proximal Point Algorithm
• Nonlinear inverse optimal transport: identifiability of the transport cost from its marginals and optimal values
• On an inverse boundary problem for mean field games
• On the implementation of a primal-dual algorithm for second order time-dependent mean field games with local couplings
• Optimal transport with proximal splitting
• Proto-differentiability of set-valued mappings and its applications in optimization
• Proximal methods for stationary mean field games with local couplings
• Random Features for High-Dimensional Nonlocal Mean-Field Games
• Recent Advances in Numerical Solutions for Hamilton-Jacobi PDEs
• Reconstructing a state-independent cost function in a mean-field game model
• Solving large-scale optimization problems with a convergence rate independent of grid size
• Sparsistency for Inverse Optimal Transport
• Splitting methods for a class of non-potential mean field games
• Taming Hyperparameter Tuning in Continuous Normalizing Flows Using the JKO Scheme
• Three-operator splitting for learning to predict equilibria in convex games

This page was built for publication: Truncated Differentiation for Inverse Potential MFGs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7284575)