SANDRA FORTINI

Sandra Fortini is Associate Professor of Statistics in the Department of Decision Sciences, at Bocconi University.

He has previously been Research fellow (1990-1994) and Researcher (1994-1995) at the Institute for the Applications of Mathematics and Informatics of the National Council of Research, and then Assistant Professor (1995-2007) at Bocconi University.

He is Fellow of the Institute of Mathematics Statistics and of the International Society of Bayesian Analysis, of the Italian Statistical Society (SIS), and of the Italian Mathematical Society (UMI).

Sandra Fortini has graduated in Mathematics at Milano University in 1989, and has gained a Master of Science in Applied Stochastic Systems in 1993 at University College of London.

 

Asymptotic properties of Bayesian and Maching Learning procedures. Predictive inference. Bayesian Nonparametric models.

Stefano Favaro; Sandra Fortini; Stefano Peluchetti
Large-width asymptotics and training dynamics of alpha-Stable Re{LU} neural networks
TRANSACTIONS ON MACHINE LEARNING RESEARCH, 2024

Bordino, Alberto; Favaro, Stefano; Fortini, Sandra
Non-asymptotic approximations of Gaussian neural networks via second-order Poincaré inequalities
Proceedings of Machine Learning Research. Volume 253: Proceedings of the 6th Symposium on Advances in Approximate Bayesian Inference, 2024

Kotecha, Gopal; Ventz, Steffen; Fortini, Sandra; Trippa, Lorenzo
Uncertainty directed factorial clinical trials
BIOSTATISTICS, Forthcoming

Bordino, Alberto; Favaro, Stefano; Fortini, Sandra
Infinitely wide limits for deep Stable neural networks: sub-linear, linear and super-linear activation functions
TRANSACTIONS ON MACHINE LEARNING RESEARCH, 2023

Sandra Fortini; Sonia Petrone
Prediction-based uncertainty quantification for exchangeable sequences
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY OF LONDON SERIES A: MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, Forthcoming

Sariev, Hristo; Fortini, Sandra; Petrone, Sonia
Infinite-color randomly reinforced urns with dominant colors
BERNOULLI, 2023

Favaro, Stefano; Fortini, Sandra; Peluchetti, Stefano
Deep Stable neural networks: large-width asymptotics and convergence rates
BERNOULLI, 2023

Bracale, Daniele; Favaro, Stefano; Fortini, Sandra; Peluchetti, Stefano
Infinite-channel deep convolutional Stable neural networks
Bayesian Deep Learning NeurIPS workshop, 2021

Bonsaglio, Marta; Fortini, Sandra; Ventz, Steffen; Trippa, Lorenzo
Approximating the operating characteristics of Bayesian Uncertainty directed trial Designs
JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2022

Fortini, Sandra; Petrone, Sonia; Sariev, Hristo
Predictive constructions based on measure-valued Pólya urn processes
MATHEMATICS, 2021

Bracale, Daniele; Favaro, Stefano; Fortini, Sandra; Peluchetti, Stefano
Large-width functional asymptotics for deep Gaussian neural networks
International Conference on Learning Representations, 2021, 2021

Stefano Favaro; Sandra Fortini; Stefano Peluchetti
Stable behaviour of infinitely wide deep neural networks
Proceedings of Machine Learning Research. Volume 108: International Conference on Artificial Intelligence and Statistics, 2020

Fortini Sandra; Petrone Sonia
Quasi‐Bayes properties of a procedure for sequential learning in mixture models
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B STATISTICAL METHODOLOGY, 2020

Fortini, Sandra; Petrone, Sonia; Sporysheva, Polina
On a notion of partially conditionally identically distributed sequences
STOCHASTIC PROCESSES AND THEIR APPLICATIONS, 2017

Fortini, Sandra; Petrone, Sonia
Predictive Characterization of Mixtures of Markov Chains
Bernoulli Journal, 2014

Fortini, Sandra; Petrone, Sonia
Predictive distribution (de Finetti's view)
Wiley StatsRef: Statistics Reference Online, 2016

Fortini, Sandra; Petrone, Sonia
Hierarchical reinforced urn processes
STATISTICS & PROBABILITY LETTERS, 2012

Fortini, Sandra; Petrone, Sonia
Predictive construction of priors in Bayesian nonparametrics
REVISTA BRASILEIRA DE PROBABILIDADE E ESTATÍSTICA, 2012

Fortini, Sandra; L. Ladelli; E. Regazzini
Central Limit Theorem with Exchangeable Summands and Mixtures of Stable Laws as Limits
BOLLETTINO DELLA UNIONE MATEMATICA ITALIANA, 2012

Cifarelli, Donato Michele; Fortini, Sandra
Recursive equations for the predictive distributions of some determinantal processes
STATISTICS & PROBABILITY LETTERS, 2011

Cerquetti A; Fortini, Sandra
A Poisson Approximation for Coloured Graphs Under Exchangeability
SANKHYA, 2006

Epifani, I; Fortini, S; Ladelli, L
A characterization for mixtures of semi-Markov processes
STATISTICS & PROBABILITY LETTERS, 2002

Fortini, Sandra; Ladelli L.; Petris G.; Regazzini E.
On mixtures of distributions of Markov chains
STOCHASTIC PROCESSES AND THEIR APPLICATIONS, 2002

Fortini, Sandra; Ruggeri F.
On the use of concentration functionin Bayesian robustness
Robusts Bayesian analysis, 2000

Fortini, Sandra; Ladelli L.; Regazzini E.
Exchangeability, predictive distributions and parametric models
SANKHYA. SERIES A, 2000

P. Berti; Fortini, Sandra; L. Ladelli; E. Regazzini; P. Rigo
On parametric models for invariant probability measures
QUADERNI DI STATISTICA, 2000

Fortini, Sandra; Ruggeri F.
Differential properties of the concentration function.
SANKHYA. SERIES A, 1997

Fortini, Sandra; Ladelli L.; Regazzini E.
A central limit problem for partially exchangeable random variables. 1996.
THEORY OF PROBABILITY AND ITS APPLICATIONS, 1996

Fortini, Sandra; Ruggeri F.
Concentration function and sensitivity to the prior
JOURNAL OF THE ITALIAN STATISTICAL SOCIETY, 1995

Fortini, Sandra; Ruggeri F.
On defining neighbowrhoods of measures through the concentration function.
SANKHYA. SERIES A, 1994

Fortini, Sandra; Ruggeri F.
Concentration functions and Bayesian robustness
JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1994

Fortini, Sandra; Ruggeri F.
Concentration function and coefficients of divergence for signed measures
JOURNAL OF THE ITALIAN STATISTICAL SOCIETY, 1993