A machine learning framework for solving high-dimensional mean field game and mean field control problems
TL;DR: In this paper, a machine learning framework for the numerical solution of potential mean field games (MFG) and mean field control (MFC) models is provided. But the numerical results are limited to the case of optimal transport and crowd motion problems.
read more
Abstract: Mean field games (MFG) and mean field control (MFC) are critical classes of multiagent models for the efficient analysis of massive populations of interacting agents. Their areas of application span topics in economics, finance, game theory, industrial engineering, crowd motion, and more. In this paper, we provide a flexible machine learning framework for the numerical solution of potential MFG and MFC models. State-of-the-art numerical methods for solving such problems utilize spatial discretization that leads to a curse of dimensionality. We approximately solve high-dimensional problems by combining Lagrangian and Eulerian viewpoints and leveraging recent advances from machine learning. More precisely, we work with a Lagrangian formulation of the problem and enforce the underlying Hamilton-Jacobi-Bellman (HJB) equation that is derived from the Eulerian formulation. Finally, a tailored neural network parameterization of the MFG/MFC solution helps us avoid any spatial discretization. Our numerical results include the approximate solution of 100-dimensional instances of optimal transport and crowd motion problems on a standard work station and a validation using a Eulerian solver in two dimensions. These results open the door to much-anticipated applications of MFG and MFC models that are beyond reach with existing numerical methods.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
An introduction to deep generative modeling
Lars Ruthotto,Eldad Haber +1 more
TL;DR: DGMs are introduced and a concise mathematical framework for modeling the three most popular approaches: normalizing flows, variational autoencoders, and generative adversarial networks is provided, which illustrates the advantages and disadvantages of these basic approaches using numerical experiments.
247
•Posted Content
How to train your neural ODE: the world of Jacobian and kinetic regularization
TL;DR: This paper introduces a theoretically-grounded combination of both optimal transport and stability regularizations which encourage neural ODEs to prefer simpler dynamics out of all the dynamics that solve a problem well, leading to faster convergence and to fewer discretizations of the solver.
221
•Posted Content
Algorithms for Solving High Dimensional PDEs: From Nonlinear Monte Carlo to Machine Learning.
TL;DR: It is demonstrated to the reader that studying PDEs as well as control and variational problems in very high dimensions might very well be among the most promising new directions in mathematics and scientific computing in the near future.
210
•Posted Content
Learning Differential Equations that are Easy to Solve
TL;DR: This work introduces a differentiable surrogate for the time cost of standard numerical solvers, using higher-order derivatives of solution trajectories that are efficient to compute with Taylor-mode automatic differentiation.
98
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
•Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
- 01 Jan 2015
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
138.5K
•Posted Content
Deep Residual Learning for Image Recognition
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
117.9K
A Stochastic Approximation Method
Herbert Robbins,Sutton Monro +1 more
TL;DR: In this article, a method for making successive experiments at levels x1, x2, ··· in such a way that xn will tend to θ in probability is presented.
•Book
Optimal Transport: Old and New
Cédric Villani
- 02 Jan 2013
TL;DR: In this paper, the authors provide a detailed description of the basic properties of optimal transport, including cyclical monotonicity and Kantorovich duality, and three examples of coupling techniques.
7.4K