A descent algorithm for the optimal control of ReLU neural network informed PDEs based on approximate directional derivatives

DOI10.1137/22M1534420MaRDI QIDQ6573014zbMATH OpenFDO

Authors Guozhi Dong, Michael Hintermüller, Kostas Papafitsoros

Publication date 16 July 2024

Published in SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/22M1534420

zbMATH Keywords

neural networksdata-driven modelsdescent algorithmsbundle-free methodsoptimal control of nonsmooth partial differential equations

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Artificial neural networks and deep learning (68T07) Numerical methods based on necessary conditions (49M05)

Recommendations

• On the identification and optimization of nonsmooth superposition operators in semilinear elliptic PDEs
• Deep learning as optimal control problems: models and numerical methods
• The ADMM-PINNs algorithmic framework for nonsmooth PDE-constrained optimization: a deep learning approach
• Optimization with learning-informed differential equation constraints and its applications
• Control of partial differential equations via physics-informed neural networks

Cites work

• scientific article; zbMATH DE number 410743 (Why is no real title available?)
• scientific article; zbMATH DE number 5703572 (Why is no real title available?)
• scientific article; zbMATH DE number 3917080 (Why is no real title available?)
• scientific article; zbMATH DE number 979133 (Why is no real title available?)
• scientific article; zbMATH DE number 5681750 (Why is no real title available?)
• scientific article; zbMATH DE number 5060482 (Why is no real title available?)
• A bundle-free implicit programming approach for a class of elliptic MPECs in function space
• CONTINUOUS PIECEWISE LINEAR FUNCTIONS
• Convergence analysis of smoothing methods for optimal control of stationary variational inequalities with control constraints
• Discretization of parameter identification in PDEs using neural networks
• Error bounds for approximations with deep ReLU neural networks in \(W^{s , p}\) norms
• Generalization of Hinging Hyperplanes
• Learning-informed parameter identification in nonlinear time-dependent PDEs
• Optimal Control in Some Variational Inequalities
• Optimal control of a non-smooth semilinear elliptic equation
• Optimization with PDE Constraints
• Optimization with learning-informed differential equation constraints and its applications
• Quantitative Magnetic Resonance Imaging: From Fingerprinting to Integrated Physics-Based Models
• Regularity and stability for the mathematical programming problem in Banach spaces
• Strong stationarity for a highly nonsmooth optimization problem with control constraints
• The Primal-Dual Active Set Strategy as a Semismooth Newton Method

Cited in

(3)

• First-Order Conditions for the Optimal Control of Learning-Informed Nonsmooth PDEs
• Optimal control of semilinear elliptic partial differential equations with non-Lipschitzian nonlinearities
• On the identification and optimization of nonsmooth superposition operators in semilinear elliptic PDEs

This page was built for publication: A descent algorithm for the optimal control of ReLU neural network informed PDEs based on approximate directional derivatives

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6573014)