scientific article; zbMATH DE number 6982921
From MaRDI portal
Publication:4558489
zbMath1467.68156arXiv1710.09513MaRDI QIDQ4558489
Cheng Tai, Qianxiao Li, Long Chen, E. Weinan
Publication date: 22 November 2018
Full work available at URL: https://arxiv.org/abs/1710.09513
Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Artificial neural networks and deep learning (68T07) Applications of optimal control and differential games (49N90) Neural nets and related approaches to inference from stochastic processes (62M45)
Related Items
Turnpike in optimal control of PDEs, ResNets, and beyond, Machine learning from a continuous viewpoint. I, On the regularized risk of distributionally robust learning over deep neural networks, Personalized Algorithm Generation: A Case Study in Learning ODE Integrators, Control on the manifolds of mappings with a view to the deep learning, Approximation capabilities of measure-preserving neural networks, Deep limits of residual neural networks, Dual non-autonomous deep convolutional neural network for image denoising, Deep learning approximation of diffeomorphisms via linear-control systems, Sparsity in long-time control of neural ODEs, A mathematical perspective of machine learning, Linear Convergence of a Policy Gradient Method for Some Finite Horizon Continuous Time Control Problems, The Mori-Zwanzig formulation of deep learning, Deep learning via dynamical systems: an approximation perspective, An artificial neural network approach to identify the parameter in a nonlinear subdiffusion model, Optimal control using to approximate probability distribution of observation set, Symplectic Runge-Kutta discretization of a regularized forward-backward sweep iteration for optimal control problems, On mathematical modeling in image reconstruction and beyond, Unnamed Item, A review on deep learning in medical image reconstruction, A modified MSA for stochastic control problems, Deep neural networks motivated by partial differential equations, Variational networks: an optimal control approach to early stopping variational methods for image restoration, Unnamed Item, Artificial neural network approximations of Cauchy inverse problem for linear PDEs, Machine Learning and Computational Mathematics, Selection dynamics for deep neural networks, Gradient convergence of deep learning-based numerical methods for BSDEs, Deep learning as optimal control problems: models and numerical methods, A sequential quadratic Hamiltonian algorithm for training explicit RK neural networks, A mean-field optimal control formulation of deep learning, Neural ODEs as the deep limit of ResNets with constant weights, Estimating adsorption isotherm parameters in chromatography via a virtual injection promoting double feed-forward neural network, Explicit Stabilized Integrators for Stiff Optimal Control Problems, Structure-preserving deep learning, 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, A Modified Method of Successive Approximations for Stochastic Recursive Optimal Control Problems, Do ideas have shape? Idea registration as the continuous limit of artificial neural networks
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Optimal control of continuity equations
- On the limited memory BFGS method for large scale optimization
- Numerical investigation of a class of Liouville control problems
- The Fokker-Planck equation. Methods of solutions and applications.
- A proposal on machine learning via dynamical systems
- Multiplier and gradient methods
- Gradient Theory of Optimal Flight Paths
- Large-Scale Machine Learning with Stochastic Gradient Descent
- The discrete-time maximum principle : a survey and some new results
- Learning Deep Architectures for AI
- Survey of Numerical Methods for Trajectory Optimization
- Method of successive approximations for solution of optimal control problems
- Stable architectures for deep neural networks
- Modifications of the method of successive approximations for solving optimal control problems
- Nonlinear Programming
- A Maximum Principle of the Pontryagin Type for Systems Described by Nonlinear Difference Equations
- Asymptotic Properties of Non-Linear Least Squares Estimators
- A Stochastic Approximation Method