activity
20162025
most citedDesigning Stable Neural Networks using Convex Analysis and ODEs

9 citations · 48 across the 28 of their papers we have counts for

collaborators
Showing 2020Show all

7 papers · 1 filter

math.OC2020

Convergence Properties of a Randomized Primal-Dual Algorithm with Applications to Parallel MRI

Eric B. Gutierrez, Claire Delplancke, Matthias J. Ehrhardt

The Stochastic Primal-Dual Hybrid Gradient (SPDHG) was proposed by Chambolle et al. (2018) and is an efficient algorithm to solve some nonsmooth large-scale optimization problems.…

cs.LG2020

Efficient Hyperparameter Tuning with Dynamic Accuracy Derivative-Free Optimization

Matthias J. Ehrhardt, Lindon Roberts

Many machine learning solutions are framed as optimization problems which rely on good hyperparameters. Algorithms for tuning these hyperparameters usually assume access to exact s…

math.OC2020

A temporal multiscale approach for MR Fingerprinting

Samuel Cortinhas, Mohammad Golbabaee, Matthias J. Ehrhardt

Quantitative MRI (qMRI) is becoming increasingly important for research and clinical applications, however, state-of-the-art reconstruction methods for qMRI are computationally pro…

eess.IV2020★ 6 cited

Multi-modality imaging with structure-promoting regularisers

Matthias J. Ehrhardt

Imaging with multiple modalities or multiple channels is becoming increasingly important for our modern society. A key tool for understanding and early diagnosis of cancer and deme…

cs.LG2020

Structure preserving deep learning

Elena Celledoni, Matthias J. Ehrhardt, Christian Etmann +4

Over the past few years, deep learning has risen to the foreground as a topic of massive interest, mainly as a result of successes obtained in solving large-scale image processing…

math.OC2020

Inexact Derivative-Free Optimization for Bilevel Learning

Matthias J. Ehrhardt, Lindon Roberts

Variational regularization techniques are dominant in the field of mathematical imaging. A drawback of these techniques is that they are dependent on a number of parameters which h…