collaborators

5 papers

cs.LG2025

Non-asymptotic approximations of Gaussian neural networks via second-order Poincaré inequalities

Alberto Bordino, Stefano Favaro, Sandra Fortini

There is a recent and growing literature on large-width asymptotic and non-asymptotic properties of deep Gaussian neural networks (NNs), namely NNs with weights initialized as Gaus…

math.ST2024

Optimal estimation of high-order missing masses, and the rare-type match problem

Stefano Favaro, Zacharie Naulet

Consider a random sample from an unknown discrete distribution on a countable alphabet , and let $(Y_{n,j})_{j\g…

math.ST2024

Random measure priors in Bayesian recovery from sketches

Mario Beraha, Stefano Favaro, Matteo Sesia

This paper introduces a Bayesian nonparametric approach to frequency recovery from lossy-compressed discrete data, leveraging all information contained in a sketch obtained through…

math.ST2024

Bayesian Nonparametric Inference for "Species-sampling" Problems

Cecilia Balocchi, Stefano Favaro, Zacharie Naulet

Given an observed sample from a population of individuals belonging to species, "species-sampling" problems (SSPs) call for estimating some features of the unknown species composit…

stat.ME2024

A Bayesian Nonparametric Approach to Species Sampling Problems with Ordering

Cecilia Balocchi, Federico Camerlenghi, Stefano Favaro

Species-sampling problems (SSPs) refer to a vast class of statistical problems calling for the estimation of (discrete) functionals of the unknown species composition of an unobser…