Optimization with learning-informed differential equation constraints and its applications
From MaRDI portal
artificial neural networkintegrated physics-based imaginglearning-informed modeloptimal controlquantitative MRIsemi-smooth Newton SQP algorithmsemilinear PDEs
Semilinear elliptic equations (35J61) Newton-type methods (49M15) Numerical solutions to equations with nonlinear operators (65J15) Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20) Numerical optimization and variational techniques (65K10) Artificial neural networks and deep learning (68T07) Nonlinear programming (90C30)
Abstract: Inspired by applications in optimal control of semilinear elliptic partial differential equations and physics-integrated imaging, differential equation constrained optimization problems with constituents that are only accessible through data-driven techniques are studied. A particular focus is on the analysis and on numerical methods for problems with machine-learned components. For a rather general context, an error analysis is provided, and particular properties resulting from artificial neural network based approximations are addressed. Moreover, for each of the two inspiring applications analytical details are presented and numerical results are provided.
Recommendations
- Control of partial differential equations via physics-informed neural networks
- Learning data-driven discretizations for partial differential equations
- Optimally weighted loss functions for solving PDEs with neural networks
- Optimality conditions for a class of inverse optimal control problems with partial differential equations
- Learning partial differential equations via data discovery and sparse optimization
Cites work
- A compressed sensing framework for magnetic resonance fingerprinting
- A mesh-independence result for semismooth Newton methods.
- A proposal on machine learning via dynamical systems
- An introduction to -convergence
- Convergence rate analysis of Tikhonov regularization for nonlinear ill-posed problems with noisy operators
- Data driven governing equations approximation using deep neural networks
- Deep learning
- DGM: a deep learning algorithm for solving partial differential equations
- Error bounds for approximations with deep ReLU neural networks in \(W^{s , p}\) norms
- Feasible and Noninterior Path‐Following in Constrained Minimization with Low Multiplier Regularity
- Global Convergence of Damped Newton's Method for Nonsmooth Equations via the Path Search
- scientific article; zbMATH DE number 5703572 (Why is no real title available?)
- scientific article; zbMATH DE number 1064079 (Why is no real title available?)
- scientific article; zbMATH DE number 1405266 (Why is no real title available?)
- scientific article; zbMATH DE number 5681750 (Why is no real title available?)
- scientific article; zbMATH DE number 2208228 (Why is no real title available?)
- scientific article; zbMATH DE number 3322278 (Why is no real title available?)
- Infinite dimensional analysis. A hitchhiker's guide.
- Local minimization, variational evolution and -convergence
- Mesh independence and fast local convergence of a primal-dual active-set method for mixed control-state constrained elliptic control problems
- Optimization methods for large-scale machine learning
- Optimization of Elliptic Systems
- Ordinary differential equations and dynamical systems
- Quantitative Magnetic Resonance Imaging: From Fingerprinting to Integrated Physics-Based Models
- Regularity and stability for the mathematical programming problem in Banach spaces
- Solving high-dimensional partial differential equations using deep learning
- Solving ill-posed inverse problems using iterative deep neural networks
- Solving inverse problems using data-driven models
- Stable architectures for deep neural networks
- The Primal-Dual Active Set Strategy as a Semismooth Newton Method
- The regularizing Levenberg-Marquardt scheme is of optimal order
- Variational Analysis in Sobolev and BV Spaces
Cited in
(11)- Iterative surrogate model optimization (ISMO): an active learning algorithm for PDE constrained optimization with deep neural networks
- Learning Enabled Constrained Black-Box Optimization
- Learning-informed parameter identification in nonlinear time-dependent PDEs
- An extended physics informed neural network for preliminary analysis of parametric optimal control problems
- On the identification and optimization of nonsmooth superposition operators in semilinear elliptic PDEs
- A descent algorithm for the optimal control of ReLU neural network informed PDEs based on approximate directional derivatives
- One-shot learning of surrogates in PDE-constrained optimization under uncertainty
- A hybrid physics-informed neural network based multiscale solver as a partial differential equation constrained optimization problem
- First-Order Conditions for the Optimal Control of Learning-Informed Nonsmooth PDEs
- Data-driven methods for quantitative imaging
- Global convergence of adjoint-optimized neural PDEs
This page was built for publication: Optimization with learning-informed differential equation constraints and its applications
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5024338)
