Inexact derivative-free optimization for bilevel learning

DOI10.1007/s10851-021-01020-8OpenAlexW3037849261MaRDI QIDQ2036198

Lindon Roberts, Matthias J. Ehrhardt

Publication date: 28 June 2021

Published in: Journal of Mathematical Imaging and Vision (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2006.12674

zbMATH Keywords

machine learningderivative-free optimizationbilevel optimizationvariational regularization

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Derivative-free methods and methods using generalized derivatives (90C56) Numerical optimization and variational techniques (65K10) Learning and adaptive systems in artificial intelligence (68T05) Numerical aspects of computer graphics, image analysis, and computational geometry (65D18) Computer science (68-XX) Information and communication theory, circuits (94-XX)

Related Items (5)

Scalable subspace methods for derivative-free nonlinear least-squares optimization ⋮ Linearly convergent bilevel optimization with single-step inner methods ⋮ Ensemble-Based Gradient Inference for Particle Methods in Optimization and Sampling ⋮ A geometric integration approach to nonsmooth, nonconvex optimisation ⋮ Bilevel Methods for Image Reconstruction

Uses Software

• DFO-GN
• HyperNOMAD

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Nonlinear total variation based noise removal algorithms
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• The structure of optimal parameters for image restoration problems
• Variational methods in imaging
• Introductory lectures on convex optimization. A basic course.
• Mathematical image processing. Translated from the German
• An algorithm for the minimization of nonsmooth nonconvex functions using inexact evaluations and its worst-case complexity
• A derivative-free Gauss-Newton method
• A Newton-CG algorithm with complexity guarantees for smooth unconstrained optimization
• Image denoising: learning the noise model via nonsmooth PDE-constrained optimization
• Trust-Region Methods Without Using Derivatives: Worst Case Complexity and the NonSmooth Case
• A Bilevel Optimization Approach for Parameter Learning in Variational Models
• Inverse Problems
• Bilevel derivative-free optimization and its application to robust optimization
• A Derivative-Free Algorithm for Least-Squares Minimization
• Bilevel Optimization with Nonsmooth Lower Level Problems
• Introduction to Derivative-Free Optimization
• Strongly Regular Generalized Equations
• Analysis of Discrete Ill-Posed Problems by Means of the L-Curve
• Variational Analysis
• Trust Region Methods
• Derivative-Free and Blackbox Optimization
• First-Order Methods in Optimization
• Improving the Flexibility and Robustness of Model-based Derivative-free Optimization Solvers
• On High-Order Multilevel Optimization Strategies
• Modern regularization methods for inverse problems
• Solving inverse problems using data-driven models
• Derivative-free optimization methods
• Adaptive Regularization Algorithms with Inexact Evaluations for Nonconvex Optimization
• An introduction to continuous optimization for imaging
• Total Generalized Variation
• Finding Optimal Algorithmic Parameters Using Derivative‐Free Optimization

This page was built for publication: Inexact derivative-free optimization for bilevel learning