A mean-field optimal control formulation of deep learning

DOI10.1007/s40687-018-0172-yzbMath1421.49021arXiv1807.01083OpenAlexW3103322710MaRDI QIDQ2319864

Jiequn Han, Qianxiao Li, E. Weinan

Publication date: 20 August 2019

Published in: Research in the Mathematical Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1807.01083

zbMATH Keywords

populationdeep learningempirical learning problemsmean-field optimal control problemmean-field Pontryagin's maximum principlepopulation risk minimization problem

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Optimality conditions for problems involving relations other than differential equations (49K21)

Related Items

Dynamic tensor approximation of high-dimensional nonlinear PDEs, The Continuous Formulation of Shallow Neural Networks as Wasserstein-Type Gradient Flows, Machine learning from a continuous viewpoint. I, Random features for high-dimensional nonlocal mean-field games, A mean field game inverse problem, Time discretizations of Wasserstein–Hamiltonian flows, Large Sample Mean-Field Stochastic Optimization, A backward SDE method for uncertainty quantification in deep learning, Implicit integration of nonlinear evolution equations on tensor manifolds, Optimal control of nonlocal continuity equations: numerical solution, Approximation capabilities of measure-preserving neural networks, Deep limits of residual neural networks, Neural network architectures using min-plus algebra for solving certain high-dimensional optimal control problems and Hamilton-Jacobi PDEs, An ODE-based neural network with Bayesian optimization, A fast proximal gradient method and convergence analysis for dynamic mean field planning, The Mori-Zwanzig formulation of deep learning, Deep learning via dynamical systems: an approximation perspective, Pontryagin's maximum principle and indirect descent method for optimal impulsive control of nonlocal transport equation, Optimal control using to approximate probability distribution of observation set, Optimal Dirichlet boundary control by Fourier neural operators applied to nonlinear optics, Computational mean-field games on manifolds, A review on deep learning in medical image reconstruction, Deep learning for ranking response surfaces with applications to optimal stopping problems, Controlling Propagation of Epidemics via Mean-Field Control, Forward stability of ResNet and its variants, Variational networks: an optimal control approach to early stopping variational methods for image restoration, A mean field games model for finite mixtures of Bernoulli and categorical distributions, Selection dynamics for deep neural networks, Spectral methods for nonlinear functionals and functional differential equations, A mean field games approach to cluster analysis, Deep learning as optimal control problems: models and numerical methods, Rank-adaptive tensor methods for high-dimensional nonlinear PDEs, The Random Feature Model for Input-Output Maps between Banach Spaces, Semiconcavity and sensitivity analysis in mean-field optimal control and applications, Stability analysis of hierarchical tensor methods for time-dependent PDEs, Neural ODEs as the deep limit of ResNets with constant weights, Shared Prior Learning of Energy-Based Models for Image Reconstruction, Structure-preserving deep learning, Continuous-domain assignment flows, A measure theoretical approach to the mean-field maximum principle for training NeurODEs, Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning, Do ideas have shape? Idea registration as the continuous limit of artificial neural networks, Disordered high-dimensional optimal control

Uses Software

• torchdiffeq

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Existence of a solution to an equation arising from the theory of mean field games
• A maximum principle for SDEs of mean-field type
• A general stochastic maximum principle for SDEs of mean-field type
• The method of characteristics for Hamilton-Jacobi equations and applications to dynamical optimization
• Forward-backward stochastic differential equations and controlled McKean-Vlasov dynamics
• The theory of differential equations. Classical and qualitative
• Mean field games
• Hamilton-Jacobi equations in infinite dimensions. I: Uniqueness of viscosity solutions
• Hamilton-Jacobi equations in infinite dimensions. II: Existence of viscosity solutions
• Hamilton-Jacobi equations in infinite dimensions. III
• Optimization of functions on certain subsets of Banach spaces
• Mean-field Pontryagin maximum principle
• Neural network with unbounded activation functions is universal approximator
• A proposal on machine learning via dynamical systems
• Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
• Mean-Field Optimal Control
• Mean Field Games and Applications
• Bellman equation and viscosity solutions for mean-field stochastic control problem
• Learning Deep Architectures for AI
• Remarks on Inequalities for Large Deviation Probabilities
• Viscosity Solutions of Hamilton-Jacobi Equations
• User’s guide to viscosity solutions of second order partial differential equations
• Approximation Methods for Nonlinear Problems with Application to Two-Point Boundary Value Problems
• Stable architectures for deep neural networks
• Sparse stabilization and control of alignment models
• Mean Field Games and Mean Field Type Control Theory
• Dynamic Programming for Optimal Control of Stochastic McKean--Vlasov Dynamics
• Dynamic programming for mean-field type control
• The elements of statistical learning. Data mining, inference, and prediction