Search Results for author: Stefano Vigogna

Found 7 papers, 0 papers with code

Neural reproducing kernel Banach spaces and representer theorems for deep networks

no code implementations13 Mar 2024 Francesca Bartolucci, Ernesto de Vito, Lorenzo Rosasco, Stefano Vigogna

Studying the function spaces defined by neural networks helps to understand the corresponding learning models and their inductive bias.

Inductive Bias

A Quantitative Functional Central Limit Theorem for Shallow Neural Networks

no code implementations29 Jun 2023 Valentina Cammarota, Domenico Marinucci, Michele Salvi, Stefano Vigogna

We prove a Quantitative Functional Central Limit Theorem for one-hidden-layer neural networks with generic activation function.

A Case of Exponential Convergence Rates for SVM

no code implementations20 May 2022 Vivien Cabannes, Stefano Vigogna

Classification is often the first problem described in introductory machine learning classes.

Classification

Understanding neural networks with reproducing kernel Banach spaces

no code implementations20 Sep 2021 Francesca Bartolucci, Ernesto de Vito, Lorenzo Rosasco, Stefano Vigogna

Characterizing the function spaces corresponding to neural networks can provide a way to understand their properties.

Multiscale regression on unknown manifolds

no code implementations13 Jan 2021 Wenjing Liao, Mauro Maggioni, Stefano Vigogna

We consider the regression problem of estimating functions on $\mathbb{R}^D$ but supported on a $d$-dimensional manifold $ \mathcal{M} \subset \mathbb{R}^D $ with $ d \ll D $.

regression

Cannot find the paper you are looking for? You can Submit a new open access paper.