Exact representation and efficient approximations of linear model predictive control laws via HardTanh type deep neural networks
From MaRDI portal
Publication:6569378
DOI10.1016/J.SYSCONLE.2024.105742zbMATH Open1545.93134MaRDI QIDQ6569378FDOQ6569378
Authors: Daniela Lupu, Ion Necoara
Publication date: 9 July 2024
Published in: Systems \& Control Letters (Search for Journal in Brave)
Recommendations
- scientific article; zbMATH DE number 829792
- Using stochastic programming to train neural network approximation of nonlinear MPC laws
- scientific article; zbMATH DE number 710399
- Learning-based Optimal Control of Constrained Switched Linear Systems using Neural Networks
- Semiglobal optimal feedback stabilization of autonomous systems via deep neural network approximation
model predictive controldeep neural networksHardTanh activation functionpiecewise affine/min-max functions
Cites Work
- QPSchur: A dual, active-set, Schur-complement method for large-scale and structured convex quadratic programming
- qpOASES: a parametric active-set algorithm for~quadratic programming
- Introductory lectures on convex optimization. A basic course.
- Deep learning
- Rate Analysis of Inexact Dual First-Order Methods Application to Dual Decomposition
- An Accelerated Dual Gradient-Projection Algorithm for Embedded Linear Model Predictive Control
- Computational complexity of inexact gradient augmented Lagrangian methods: application to constrained MPC
- Introduction to Piecewise Differentiable Equations
- The explicit linear quadratic regulator for constrained systems
- Multilayer feedforward networks are universal approximators
- Irredundant lattice representations of continuous piecewise affine functions
- Lipschitz Certificates for Layered Network Structures Driven by Averaged Activation Operators
- Temporal deep unfolding for constrained nonlinear stochastic optimal control
This page was built for publication: Exact representation and efficient approximations of linear model predictive control laws via HardTanh type deep neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6569378)