Next-generation radio interferometers like the Square Kilometer Array have the potential to
unlock scientific discoveries thanks to their unprecedented angular resolution and …

Plug-and-Play (PnP) methods are a class of efficient iterative methods that aim to combine
data fidelity terms and deep denoisers using classical optimization algorithms, such as ISTA …

Federated learning (FL) has emerged as a key technique for distributed machine learning
(ML). Most literature on FL has focused on ML model training for (i) a single task/model, with …

Proximal operators are ubiquitous in inverse problems, commonly appearing as part of
algorithmic strategies to regularize problems that are otherwise ill-posed. Modern deep …

Variational regularisation is the primary method for solving inverse problems, and recently
there has been considerable work leveraging deeply learned regularisation for enhanced …

Inverse problems are fundamental in fields like medical imaging, geophysics, and
computerized tomography, aiming to recover unknown quantities from observed data …

We propose to enhance 1-weakly convex ridge regularizers for image reconstruction by
incorporating spatial adaptivity. To this end, we resort to a neural network that generates a …

This article presents a novel approach to image restoration utilizing a unique non-convex l
1/2-TV regularization model. This model integrates the l 1/2-quasi norm as a regularization …

In the Plug-and-Play (PnP) method, a denoiser is used as a regularizer within classical
proximal algorithms for image reconstruction. It is known that a broad class of linear …

Variational regularization is a classical technique to solve statistical inference tasks and
inverse problems, with modern data-driven approaches parameterizing regularizers via …