Relaxation approach for learning neural network regularizers for a class of identification problems

DOI10.1088/1361-6420/AD0756arXiv2109.11658OpenAlexW4388196116MaRDI QIDQ6087358

Sébastien Court

Publication date: 15 November 2023

Published in: Inverse Problems (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2109.11658

zbMATH Keywords

regularizationneural networksidentification problemoptimal control theorylearning problemsdata-driven optimization

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Miscellaneous topics in calculus of variations and optimal control (49Nxx)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Design of the monodomain model by artificial neural networks
• Optimal control of PDEs using physics-informed neural networks
• Learning nonlocal regularization operators
• Learning an optimal feedback operator semiglobally stabilizing semilinear parabolic equations
• Neural network architectures using min-plus algebra for solving certain high-dimensional optimal control problems and Hamilton-Jacobi PDEs
• Event-triggered optimal nonlinear systems control based on state observer and neural network
• A Bilevel Optimization Approach for Parameter Learning in Variational Models
• The Barzilai and Borwein Gradient Method for the Large Scale Unconstrained Minimization Problem
• Optimization with PDE Constraints
• Solving ill-posed inverse problems using iterative deep neural networks
• A bilevel approach for parameter learning in inverse problems
• Feedback control of minimum‐time optimal control problems using neural networks
• Semiglobal optimal feedback stabilization of autonomous systems via deep neural network approximation
• Deep Neural Network Approximation Theory
• NETT: solving inverse problems with deep neural networks
• Learning regularization parameters of inverse problems via deep neural networks
• Modern regularization methods for inverse problems
• Learning-informed parameter identification in nonlinear time-dependent PDEs
• An extended physics informed neural network for preliminary analysis of parametric optimal control problems
• Handbook of Mathematical Models and Algorithms in Computer Vision and Imaging

This page was built for publication: Relaxation approach for learning neural network regularizers for a class of identification problems