Explainable bilevel optimization: an application to the Helsinki Deblur Challenge

DOI10.3934/ipi.2022055zbMath1515.94013arXiv2210.10050MaRDI QIDQ6169501

Giorgia Franchini, Marco Prato, Silvia Bonettini, Unnamed Author

Publication date: 12 July 2023

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

Full work available at URL: https://arxiv.org/abs/2210.10050

zbMATH Keywords

bilevel optimizationperformance predictorblind deconvolution methodsGreenAIHelsinki Deblur Challenge

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Nonlinear programming (90C30) Learning and adaptive systems in artificial intelligence (68T05) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Related Items (1)

Bilevel optimal parameter learning for a high-order nonlocal multiframe super-resolution problem

Cites Work

• Smooth minimization of non-smooth functions
• The Little Engine that Could: Regularization by Denoising (RED)
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• On the convergence of the iterates of the ``fast iterative shrinkage/thresholding algorithm
• Fields of experts
• Projected subgradient methods with non-Euclidean distances for non-differentiable convex minimization and variational inequalities
• Variational networks: an optimal control approach to early stopping variational methods for image restoration
• Ritz-like values in steplength selections for stochastic gradient methods
• A Bilevel Optimization Approach for Parameter Learning in Variational Models
• Bilevel Optimization with Nonsmooth Lower Level Problems
• New convergence results for the scaled gradient projection method
• A scaled gradient projection method for constrained image deblurring
• Efficient gradient projection methods for edge-preserving removal of Poisson noise
• Insights Into Analysis Operator Learning: From Patch-Based Sparse Models to Higher Order MRFs
• Inertial Variable Metric Techniques for the Inexact Forward--Backward Algorithm
• Computed tomography with view angle estimation using uncertainty quantification
• Deep unfolding of a proximal interior point method for image restoration
• Solving inverse problems using data-driven models
• Adaptive FISTA for Nonconvex Optimization
• Neural architecture search via standard machine learning methodologies

This page was built for publication: Explainable bilevel optimization: an application to the Helsinki Deblur Challenge