DeepSets and their derivative networks for solving symmetric PDEs
DOI10.1007/S10915-022-01796-WOpenAlexW3135321366WikidataQ114225575 ScholiaQ114225575MaRDI QIDQ2148121FDOQ2148121
Maximilien Germain, Huyên Pham, Mathieu Laurière, Xavier Warin
Publication date: 21 June 2022
Published in: Journal of Scientific Computing (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2103.00838
exchangeabilitymean-field controldeep backward schemepermutation-invariant PDEssymmetric neural networks
Stochastic analysis (60Hxx) Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems (65Mxx)
Cites Work
- Mean field games
- Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
- On the system of partial differential equations arising in mean field type control
- Mean Field Games: Numerical Methods
- Adapted solution of a backward stochastic differential equation
- Robust Markowitz mean‐variance portfolio selection under ambiguous covariance matrix
- Mean field games and systemic risk
- Probabilistic Theory of Mean Field Games with Applications I
- Dynamic Programming for Optimal Control of Stochastic McKean--Vlasov Dynamics
- On the area of the symmetry orbits of cosmological spacetimes with toroidal or hyperbolic symmetry
- Deep backward schemes for high-dimensional nonlinear PDEs
- Solving high-dimensional partial differential equations using deep learning
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
- Machine learning for semi linear PDEs
- Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games I: The Ergodic Case
- Limit Theory for Controlled McKean--Vlasov Dynamics
- Neural networks-based backward scheme for fully nonlinear PDEs
- Finite Dimensional Approximations of Hamilton--Jacobi--Bellman Equations in Spaces of Probability Measures
- A weak martingale approach to linear-quadratic Mckean-Vlasov stochastic control problems
- Extended mean field control problem: a propagation of chaos result
- Approximation Error Analysis of Some Deep Backward Schemes for Nonlinear PDEs
- Numerical resolution of McKean-Vlasov FBSDEs using neural networks
Cited In (8)
- Importance sampling for the empirical measure of weakly interacting diffusions
- A fast iterative PDE-based algorithm for feedback controls of nonsmooth mean-field control problems
- A level-set approach to the control of state-constrained McKean-Vlasov equations: application to renewable energy storage and portfolio selection
- DeepSets and their derivative networks for solving symmetric PDEs
- Recent developments in machine learning methods for stochastic control and games
- Symmetrized two-scale finite element discretizations for partial differential equations with symmetric solutions
- Derivative-informed projected neural networks for high-dimensional parametric maps governed by PDEs
- Dosnet as a non-black-box PDE solver: when deep learning meets operator splitting
Uses Software
This page was built for publication: DeepSets and their derivative networks for solving symmetric PDEs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2148121)
