Learning High-Dimensional McKean–Vlasov Forward-Backward Stochastic Differential Equations with General Distribution Dependence
From MaRDI portal
(Redirected from Publication:6184510)
convergence analysisdeep BSDEfictitious playmaximum mean discrepancyMcKean-Vlasov FBSDEmean-field games
Mean field games and control (49N80) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35) Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems (65M99) Analysis of algorithms and problem complexity (68Q25) Artificial neural networks and deep learning (68T07) Optimal stochastic control (93E20)
Abstract: One of the core problems in mean-field control and mean-field games is to solve the corresponding McKean-Vlasov forward-backward stochastic differential equations (MV-FBSDEs). Most existing methods are tailored to special cases in which the mean-field interaction only depends on expectation or other moments and thus inadequate to solve problems when the mean-field interaction has full distribution dependence. In this paper, we propose a novel deep learning method for computing MV-FBSDEs with a general form of mean-field interactions. Specifically, built on fictitious play, we recast the problem into repeatedly solving standard FBSDEs with explicit coefficient functions. These coefficient functions are used to approximate the MV-FBSDEs' model coefficients with full distribution dependence, and are updated by solving another supervising learning problem using training data simulated from the last iteration's FBSDE solutions. We use deep neural networks to solve standard BSDEs and approximate coefficient functions in order to solve high-dimensional MV-FBSDEs. Under proper assumptions on the learned functions, we prove that the convergence of the proposed method is free of the curse of dimensionality (CoD) by using a class of integral probability metrics previously developed in [Han, Hu and Long, arXiv:2104.12036]. The proved theorem shows the advantage of the method in high dimensions. We present the numerical performance in high-dimensional MV-FBSDE problems, including a mean-field game example of the well-known Cucker-Smale model whose cost depends on the full distribution of the forward process.
Recommendations
- Numerical resolution of McKean-Vlasov FBSDEs using neural networks
- Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games. II: The finite horizon case
- A cubature based algorithm to solve decoupled McKean-Vlasov forward-backward stochastic differential equations
- Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games. I: The ergodic case
- CEMRACS 2017: numerical probabilistic approach to MFG
Cites work
- A class of dimension-free metrics for the convergence of empirical measures
- A cubature based algorithm to solve decoupled McKean-Vlasov forward-backward stochastic differential equations
- A Cucker-Smale inspired deterministic mean field game with velocity interactions
- Backward stochastic differential equations. From linear to fully nonlinear theory
- Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games. II: The finite horizon case
- Convergence of deep fictitious play for stochastic differential games
- Convergence of some mean field games systems to aggregation and flocking models
- Convergence of the deep BSDE method for coupled FBSDEs
- Deep backward schemes for high-dimensional nonlinear PDEs
- Deep fictitious play for stochastic differential games
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Forward-backward stochastic differential equations and controlled McKean-Vlasov dynamics
- scientific article; zbMATH DE number 3069635 (Why is no real title available?)
- Income and wealth distribution in macroeconomics: a continuous-time approach
- Integral Probability Metrics and Their Generating Classes of Functions
- Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
- Large-Population Cost-Coupled LQG Problems With Nonuniform Agents: Individual-Mass Behavior and Decentralized \varepsilon-Nash Equilibria
- Mean field forward-backward stochastic differential equations
- Mean field games
- Mean field games and applications: numerical aspects
- Mean field games. I: The stationary case
- Mean field games. II: Finite horizon and optimal control
- Numerical method for FBSDEs of McKean-Vlasov type
- Numerical resolution of McKean-Vlasov FBSDEs using neural networks
- On the mathematics of emergence
- Probabilistic analysis of mean-field games
- Probabilistic theory of mean field games with applications I. Mean field FBSDEs, control, and games
- Solving high-dimensional partial differential equations using deep learning
- The Barron space and the flow-induced function spaces for neural network models
- Time discretization and Markovian iteration for coupled FBSDEs
Cited in
(9)- A deep learning method for solving multi-dimensional coupled forward-backward doubly SDEs
- \textit{A posteriori} error estimates for fully coupled McKean-Vlasov forward-backward SDEs
- Propagation of chaos for mean field Schrödinger problems
- Actor-critic learning for mean-field control in continuous time
- A deep learning method for optimal investment under relative performance criteria among heterogeneous agents
- Finite-agent stochastic differential games on large graphs. I: The linear-quadratic case
- Deep learning for conditional McKean-Vlasov jump diffusions
- XGBoost Monte Carlo high-order regression method for high-dimensional decoupled forward backward stochastic differential equations
- Solving McKean-Vlasov stochastic differential equations by a deep learning particle method
This page was built for publication: Learning High-Dimensional McKean–Vlasov Forward-Backward Stochastic Differential Equations with General Distribution Dependence
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6184510)
