Investigating bi-level optimization for learning and vision from a unified perspective: A survey and beyond
Bi-Level Optimization (BLO) is originated from the area of economic game theory and then
introduced into the optimization community. BLO is able to handle problems with a …
introduced into the optimization community. BLO is able to handle problems with a …
Hyperparameter optimization with approximate gradient
F Pedregosa - International conference on machine learning, 2016 - proceedings.mlr.press
Most models in machine learning contain at least one hyperparameter to control for model
complexity. Choosing an appropriate set of hyperparameters is both crucial in terms of …
complexity. Choosing an appropriate set of hyperparameters is both crucial in terms of …
Adversarial regularizers in inverse problems
S Lunz, O Öktem, CB Schönlieb - Advances in neural …, 2018 - proceedings.neurips.cc
Inverse Problems in medical imaging and computer vision are traditionally solved using
purely model-based methods. Among those variational regularization models are one of the …
purely model-based methods. Among those variational regularization models are one of the …
Deep learning computed tomography: Learning projection-domain weights from image domain in limited angle problems
In this paper, we present a new deep learning framework for 3-D tomographic
reconstruction. To this end, we map filtered back-projection-type algorithms to neural …
reconstruction. To this end, we map filtered back-projection-type algorithms to neural …
[HTML][HTML] Higher-order total variation approaches and generalisations
Over the last decades, the total variation (TV) has evolved to be one of the most broadly-
used regularisation functionals for inverse problems, in particular for imaging applications …
used regularisation functionals for inverse problems, in particular for imaging applications …
Self-tuning networks: Bilevel optimization of hyperparameters using structured best-response functions
Hyperparameter optimization can be formulated as a bilevel optimization problem, where
the optimal parameters on the training set depend on the hyperparameters. We aim to adapt …
the optimal parameters on the training set depend on the hyperparameters. We aim to adapt …
Exact and inexact subsampled Newton methods for optimization
R Bollapragada, RH Byrd… - IMA Journal of Numerical …, 2019 - academic.oup.com
The paper studies the solution of stochastic optimization problems in which approximations
to the gradient and Hessian are obtained through subsampling. We first consider Newton …
to the gradient and Hessian are obtained through subsampling. We first consider Newton …
Computational medical image reconstruction techniques: a comprehensive review
Medical image reconstruction (MIR) is the elementary way of producing an internal 3D view
of the patient. MIR is inherently ill-posed, and various approaches have been proposed to …
of the patient. MIR is inherently ill-posed, and various approaches have been proposed to …
Bilevel methods for image reconstruction
C Crockett, JA Fessler - Foundations and Trends® in Signal …, 2022 - nowpublishers.com
This review discusses methods for learning parameters for image reconstruction problems
using bilevel formulations. Image reconstruction typically involves optimizing a cost function …
using bilevel formulations. Image reconstruction typically involves optimizing a cost function …
Learning regularization parameters of inverse problems via deep neural networks
In this work, we describe a new approach that uses deep neural networks (DNN) to obtain
regularization parameters for solving inverse problems. We consider a supervised learning …
regularization parameters for solving inverse problems. We consider a supervised learning …