Luca Galimberti

collaborators

2 papers

math.FA2026

$L^{p}$ approximation results for infinite dimensional Neural Networks

Luca Galimberti

Leveraging the neural architectures which we introduced in arXiv:2109.13512v4, we show a global universal approximation theorem in the topology of $L^{p} (μ)$ , where $1 \leq p < \infty$ a…

stat.ML2025

Learning from one graph: transductive learning guarantees via the geometry of small random worlds

Nils Detering, Luca Galimberti, Anastasis Kratsios +2

Since their introduction by Kipf and Welling in $2017$ , a primary use of graph convolutional networks is transductive node classification, where missing labels are inferred within…

Lp approximation results for infinite dimensional Neural Networks

Learning from one graph: transductive learning guarantees via the geometry of small random worlds

$L^{p}$ approximation results for infinite dimensional Neural Networks