3 papers
math.OC2026
On the existence of optimal multi-valued decoders and their accuracy bounds for ill-posed inverse problems
Nina Maria Gottschling, Paolo Campodonico, Vegard Antun +1
Ill-posed inverse problems occur everywhere in the sciences including medical imaging, radar, astronomy etc., yielding underdetermined or ill-posed linear (non-linear) reconstructi…
cs.LG2024
Achieving Data Efficient Neural Networks with Hybrid Concept-based Models
Tobias A. Opsahl, Vegard Antun
Most datasets used for supervised machine learning consist of a single label per data point. However, in cases where more information than just the class label is available, would…
cs.LG2024
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…