Maximum principle based algorithms for deep learning
From MaRDI portal
Publication:4558489
zbMATH Open1467.68156arXiv1710.09513MaRDI QIDQ4558489FDOQ4558489
Authors: Qianxiao Li, Long Chen, Cheng Tai, Weinan E 
Publication date: 22 November 2018
Full work available at URL: https://arxiv.org/abs/1710.09513
Recommendations
- Dynamical Systems andOptimal Control Approach to Deep Learning
- A mean-field optimal control formulation of deep learning
- Deep learning as optimal control problems: models and numerical methods
- Substantiation of the backpropagation technique via the Hamilton-Pontryagin formalism for training nonconvex nonsmooth neural networks
- Selection dynamics for deep neural networks
Artificial neural networks and deep learning (68T07) Neural nets and related approaches to inference from stochastic processes (62M45) Applications of optimal control and differential games (49N90)
Cites Work
- Adaptive subgradient methods for online learning and stochastic optimization
- Learning deep architectures for AI
- Title not available (Why is that?)
- On the limited memory BFGS method for large scale optimization
- Asymptotic Properties of Non-Linear Least Squares Estimators
- A Stochastic Approximation Method
- Deep learning
- Multiplier and gradient methods
- Title not available (Why is that?)
- Survey of Numerical Methods for Trajectory Optimization
- Introduction to the mathematical theory of control
- Nonlinear Programming
- The Fokker-Planck equation. Methods of solutions and applications.
- Optimal control of continuity equations
- Calculus of variations and optimal control theory. A concise introduction
- Method of successive approximations for solution of optimal control problems
- Modifications of the method of successive approximations for solving optimal control problems
- The discrete-time maximum principle : a survey and some new results
- Large-scale machine learning with stochastic gradient descent
- A Maximum Principle of the Pontryagin Type for Systems Described by Nonlinear Difference Equations
- Title not available (Why is that?)
- The maximum principle in optimal control, then and now
- Gradient Theory of Optimal Flight Paths
- Stable architectures for deep neural networks
- A proposal on machine learning via dynamical systems
- Numerical investigation of a class of Liouville control problems
- Title not available (Why is that?)
Cited In (49)
- Variational networks: an optimal control approach to early stopping variational methods for image restoration
- A mean-field optimal control formulation of deep learning
- A measure theoretical approach to the mean-field maximum principle for training NeurODEs
- Principled deep neural network training through linear programming
- An optimal control framework for adaptive neural ODEs
- Deep learning approximation of diffeomorphisms via linear-control systems
- Sparsity in long-time control of neural ODEs
- Machine learning from a continuous viewpoint. I
- Control on the manifolds of mappings with a view to the deep learning
- Do ideas have shape? Idea registration as the continuous limit of artificial neural networks
- Machine learning and computational mathematics
- A Max-Sum algorithm for training discrete neural networks
- Deep limits of residual neural networks
- Title not available (Why is that?)
- A modified MSA for stochastic control problems
- Selection dynamics for deep neural networks
- Deep neural networks motivated by partial differential equations
- Linear Convergence of a Policy Gradient Method for Some Finite Horizon Continuous Time Control Problems
- Turnpike in optimal control of PDEs, ResNets, and beyond
- The Mori-Zwanzig formulation of deep learning
- Maximal Function Pooling with Applications
- Deep learning as optimal control problems: models and numerical methods
- Approximation capabilities of measure-preserving neural networks
- An artificial neural network approach to identify the parameter in a nonlinear subdiffusion model
- Personalized algorithm generation: a case study in learning ODE integrators
- Deep learning via dynamical systems: an approximation perspective
- Title not available (Why is that?)
- Optimal control using to approximate probability distribution of observation set
- Gradient convergence of deep learning-based numerical methods for BSDEs
- On mathematical modeling in image reconstruction and beyond
- Neural ODEs as the deep limit of ResNets with constant weights
- Explicit Stabilized Integrators for Stiff Optimal Control Problems
- On the regularized risk of distributionally robust learning over deep neural networks
- A modified method of successive approximations for stochastic recursive optimal control problems
- Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning
- Substantiation of the backpropagation technique via the Hamilton-Pontryagin formalism for training nonconvex nonsmooth neural networks
- Dual non-autonomous deep convolutional neural network for image denoising
- Concurrent learning for adaptive Pontryagin's maximum principle of nonlinear systems with inequality constraints
- A sequential quadratic Hamiltonian algorithm for training explicit RK neural networks
- Dynamical Systems andOptimal Control Approach to Deep Learning
- Efficient and stable SAV-based methods for gradient flows arising from deep learning
- Symplectic Runge-Kutta discretization of a regularized forward-backward sweep iteration for optimal control problems
- A review on deep learning in medical image reconstruction
- Predict globally, correct locally: parallel-in-time optimization of neural networks
- Estimating adsorption isotherm parameters in chromatography via a virtual injection promoting double feed-forward neural network
- Structure-preserving deep learning
- An optimal control method to compute the most likely transition path for stochastic dynamical systems with jumps
- Artificial neural network approximations of Cauchy inverse problem for linear PDEs
- A mathematical perspective of machine learning
Uses Software
This page was built for publication: Maximum principle based algorithms for deep learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4558489)
