Despite the large success of deep neural networks (DNN) in recent years, most neural
networks still lack mathematical guarantees in terms of stability. For instance, DNNs are …

We study two-layer neural networks whose domain and range are Banach spaces with
separable preduals. In addition, we assume that the image space is equipped with a partial …

Learned iterative reconstructions hold great promise to accelerate tomographic imaging with
empirical robustness to model perturbations. Nevertheless, an adoption for photoacoustic …

We study the problem of deconvolution for light-sheet microscopy, where the data is
corrupted by spatially varying blur and a combination of Poisson and Gaussian noise. The …

We formulate a physics-informed compressed sensing (PICS) method for the reconstruction
of velocity fields from noisy and sparse phase-contrast magnetic resonance signals. The …

Inverse problems are in many cases solved with optimization techniques. When the
underlying model is linear, first-order gradient methods are usually sufficient. With nonlinear …

In this paper, we propose to use the general L 2-based Sobolev norms, ie, H s norms where
s∈ R, to measure the data discrepancy due to noise in image processing tasks that are …

We consider a bilevel learning framework for learning linear operators. In this framework, the
learnable parameters are optimized via a loss function that also depends on the minimizer of …

We provide a state-of-the-art analysis of acoustic side channels, cover all the significant
academic research in the area, discuss their security implications and countermeasures …

This paper is concerned with variational regularization of inverse problems where both the
data and the forward operator are given only approximately. We propose a general …