A sequential quadratic Hamiltonian algorithm for training explicit RK neural networks
discrete Pontryagin maximum principlemethod of successive approximationsnumerical optimizationresidual neural networksRunge-Kutta neural networkssequential quadratic Hamiltonian algorithm
Existence theories for optimal control problems involving ordinary differential equations (49J15) Optimality conditions for problems involving ordinary differential equations (49K15) Numerical methods based on necessary conditions (49M05) Numerical optimization and variational techniques (65K10) Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)
- Substantiation of the backpropagation technique via the Hamilton-Pontryagin formalism for training nonconvex nonsmooth neural networks
- New comprehensive learning method based on an LM-quasi-Newton algorithm applied to feed-forward neural networks
- Layer-Parallel Training of Deep Residual Neural Networks
- scientific article; zbMATH DE number 1054676
- Training recurrent neural networks by sequential least squares and the alternating direction method of multipliers
- A Limited Memory Algorithm for Bound Constrained Optimization
- A Maximum Principle of the Pontryagin Type for Systems Described by Nonlinear Difference Equations
- A sequential quadratic Hamiltonian method for solving parabolic optimal control problems with discontinuous cost functionals
- A sequential quadratic Hamiltonian scheme for solving non-smooth quantum control problems with sparsity
- An algorithm for the method of successive approximations in optimal control problems
- Hedonic housing prices and the demand for clean air
- scientific article; zbMATH DE number 3118979 (Why is no real title available?)
- scientific article; zbMATH DE number 3167340 (Why is no real title available?)
- scientific article; zbMATH DE number 5937962 (Why is no real title available?)
- scientific article; zbMATH DE number 5060482 (Why is no real title available?)
- L. S. Pontryagin's maximum principle in the theory of optimal systems. I--III
- Local convergence of an algorithm for solving optimal control problems
- Maximum principle based algorithms for deep learning
- Method of successive approximations for solution of optimal control problems
- Modelling with ordinary differential equations. A comprehensive approach
- Neural networks and deep learning. A textbook
- On a method of successive approximations for the solution of problems of optimal control
- On global convergence of an algorithm for optimal control
- On the proof of Pontryagin's maximum principle by means of needle variations
- On the SQH Scheme to Solve Nonsmooth PDE Optimal Control Problems
- Runge-Kutta methods in optimal control and the transformed adjoint system
- Stable architectures for deep neural networks
- Symplectic Runge-Kutta discretization of a regularized forward-backward sweep iteration for optimal control problems
- On the SQH method for solving optimal control problems with non-smooth state cost functionals or constraints
- Hamiltonian Deep Neural Networks Guaranteeing Nonvanishing Gradients by Design
- Accuracy Estimates for Bilinear Optimal Control Problems Governed by Ordinary Differential Equations
- Pointwise error estimates of numerical solutions to linear quadratic optimal control problems
- The Pontryagin maximum principle for training convolutional neural networks
This page was built for publication: A sequential quadratic Hamiltonian algorithm for training explicit RK neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2068636)
