38 citations · 71 across the 13 of their papers we have counts for
17 papers
A Lipschitz spaces view of infinitely wide shallow neural networks
Francesca Bartolucci, Marcello Carioni, José A. Iglesias +3
We revisit the mean field parametrization of shallow neural networks, using signed measures on unbounded parameter spaces and duality pairings that take into account the regularity…
Neural reproducing kernel Banach spaces and representer theorems for deep networks
Francesca Bartolucci, Ernesto De Vito, Lorenzo Rosasco +1
Characterizing the function spaces defined by neural networks helps understanding the corresponding learning models and their inductive bias. While in some limits neural networks c…
Uncovering the limits of uniqueness in sampled Gabor phase retrieval: A dense set of counterexamples in
Rima Alaifari, Francesca Bartolucci, Matthias Wellershoff
Sampled Gabor phase retrieval - the problem of recovering a square-integrable signal from the magnitude of its Gabor transform sampled on a lattice - is a fundamental problem in si…
Representation Equivalent Neural Operators: a Framework for Alias-free Operator Learning
Francesca Bartolucci, Emmanuel de Bézenac, Bogdan Raonić +3
Recently, operator learning, or learning mappings between infinite-dimensional function spaces, has garnered significant attention, notably in relation to learning partial differen…
Unique wavelet sign retrieval from samples without bandlimiting
Rima Alaifari, Francesca Bartolucci, Matthias Wellershoff
We study the problem of recovering a signal from magnitudes of its wavelet frame coefficients when the analyzing wavelet is real-valued. We show that every real-valued signal can b…
Convolutional Neural Operators for robust and accurate learning of PDEs
Bogdan Raonić, Roberto Molinaro, Tim De Ryck +5
Although very successfully used in conventional machine learning, convolution based neural network architectures -- believed to be inconsistent in function space -- have been large…