collaborators

13 papers

cs.LG2026

Approximation Rates for Metaplectic Neural Networks

Ahmed Abdeljawad, Marcello Carioni, Elena Cordero

In this paper we develop quantitative approximation results for shallow neural networks constructed using a dictionary based on metaplectic operators. First, we extend the concept…

math.OC2026

A Distributionally Robust Framework for Learned Reconstructions in Inverse Problems

Floor van Maarschalkerwaart, Subhadip Mukherjee, Christoph Brune +1

Learned reconstruction operators for inverse problems are typically trained under a fixed noise model, and generalize poorly when the distribution during testing differs from the o…

cs.LG2026

Multi-Headed Transformer Architectures as Time-dependent Wasserstein Gradient Flows

Alex Massucco, Leonardo Del Grande, Marcello Carioni +2

In recent years, transformer architectures have revolutionized the field of language processing, opening the door to previously unforeseen possibilities. However, from a theoretica…

math.OC2026

Atomic Gradient Flows: Gradient Flows on Sparse Representations

Christian Amend, Marcello Carioni, Konstantinos Zemas

One of the most popular approaches for solving total variation-regularized optimization problems in the space of measures are Particle Gradient Flows (PGFs). These restrict the pro…

math.OC2026

A Dual Certificate Approach to Sparsity in Infinite-Width Shallow Neural Networks

Leonardo Del Grande, Christoph Brune, Marcello Carioni

In this paper, we study total variation (TV)-regularized training of infinite-width shallow ReLU neural networks, formulated as a convex optimization problem over measures on the u…

math.FA2025

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…