795 citations · 1.4k across the 64 of their papers we have counts for
6 papers · 1 filter
Deep Neural Networks Are Effective At Learning High-Dimensional Hilbert-Valued Functions From Limited Data
Ben Adcock, Simone Brugiapaglia, Nick Dexter +1
Accurate approximation of scalar-valued functions from sample points is a key task in computational science. Recently, machine learning with Deep Neural Networks (DNNs) has emerged…
Improved recovery guarantees and sampling strategies for TV minimization in compressive imaging
Ben Adcock, Nick Dexter, Qinghong Xu
In this paper, we consider the use of Total Variation (TV) minimization for compressive imaging; that is, image reconstruction from subsampled measurements. Focusing on two importa…
The benefits of acting locally: Reconstruction algorithms for sparse in levels signals with stable and robust recovery guarantees
Ben Adcock, Simone Brugiapaglia, Matthew King-Roskamp
The sparsity in levels model recently inspired a new generation of effective acquisition and reconstruction modalities for compressive imaging. Moreover, it naturally arises in var…
The gap between theory and practice in function approximation with deep neural networks
Ben Adcock, Nick Dexter
Deep learning (DL) is transforming industry as decision-making processes are being automated by deep neural networks (DNNs) trained on real-world data. Driven partly by rapidly-exp…
The troublesome kernel -- On hallucinations, no free lunches and the accuracy-stability trade-off in inverse problems
Nina M. Gottschling, Vegard Antun, Anders C. Hansen +1
Methods inspired by Artificial Intelligence (AI) are starting to fundamentally change computational science and engineering through breakthrough performances on challenging problem…
Frame approximation with bounded coefficients
Ben Adcock, Mohsen Seifi
Due to their flexibility, frames of Hilbert spaces are attractive alternatives to bases in approximation schemes for problems where identifying a basis is not straightforward or ev…