A Parameterized Stochastic Hamiltonian Process on Graphs with Two-Point Boundary Conditions

DOI10.48550/ARXIV.2610.40497MaRDI QIDQ7409172arXivFDO

Authors Yaxin Feng, Haomin Zhou, Yang Xiang

Publication date 29 October 2026

Published in arXiv

Tldr This paper presents a Lagrangian framework to solve Wasserstein Hamiltonian flows under two-point boundary conditions on graphs. We introduce the stochastic Hamiltonian process (SHP), parameterized by neural networks, which overcomes memory and computational bottlenecks of classical density-based solvers on large-scale graphs.

Full work available at URL https://doi.org/10.48550/ARXIV.2610.40497

arXiv classification

math.NA

Cites work

• A discrete Schrödinger equation via optimal transport on graphs
• A gradient structure for reaction–diffusion systems and for energy-drift-diffusion systems
• Analysis of a Finite State Many Player Game Using Its Master Equation
• Continuous time finite state mean field games
• Convergence, fluctuations and large deviations for finite state mean field games via the master equation
• Deep neural network solution for finite state mean field game with error estimation
• Deterministic mean field games on networks: a Lagrangian approach
• Discrete Mean Field Games on Finite Graphs as Initial Value Optimization
• Discrete time, finite state space mean field games
• Dynamical Schrödinger bridge problems on graphs
• Entropy dissipation of Fokker-Planck equations on graphs
• Fokker-Planck equations for a free energy functional or Markov process on a graph
• From denoising diffusions to denoising Markov models
• Gradient flows of the entropy for finite Markov chains
• Handbook of Graph Theory
• Modeling of chemical reaction systems with detailed balance using gradient structures
• On the relation between gradient flows and the large-deviation principle, with applications to Markov chains and diffusion
• Opinion dynamics in social networks through mean-field games
• Optimal Transportation with Traffic Congestion and Wardrop Equilibria
• Probabilistic approach to finite state mean field games
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Stationary mean field games systems defined on networks
• Wasserstein Hamiltonian flows
• What is a stochastic Hamiltonian process on finite graph? An optimal transport answer

This page was built for publication: A Parameterized Stochastic Hamiltonian Process on Graphs with Two-Point Boundary Conditions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7409172)