Matteo Sordello

PhD Student in Statistics

Wharton School, UPenn

Biography

I am a PhD Student in the Statistics Department at the Wharton School, University of Pennsylvania, under the supervision of Professor Weijie Su.

Before coming to Penn, I studied Mathematics at the University of Turin and Statistics at Collegio Carlo Alberto, where I completed my Master’s thesis under the supervision of Professor Matteo Ruggiero.

My personal email address is: matteo.sordello91 AT gmail DOT com

Interests

Optimization
Machine Learning
MCMC Sampling
Active Learning

Education

PhD in Statistics, 2021
The Wharton School, University of Pennsylvania
M.Sc. in Mathematics with emphasis in Probability, 2015
University of Torino
M.A. in Statistics and Applied Mathematics, 2015
Collegio Carlo Alberto
B.Sc. in Mathematics, 2013
University of Torino

Publications

Privacy Amplification via Iteration for Shuffled and Online PNSGD

In this paper, we consider the framework of privacy amplification via iteration, which is originally proposed by Feldman et al. and …

Matteo Sordello, Zhiqi Bu, Jinshuo Dong

PDF Slides

A Test for Differential Ascertainment in Case-Control Studies with Application to Child Maltreatment

We propose a method to test for the presence of differential ascertainment in case-control studies, when data are collected by multiple …

Matteo Sordello, Dylan S. Small

PDF DOI

A Bernstein type inequality for sums of selections from three dimensional arrays

We consider the three dimensional array $\mathcal{A} = ${$a_{i,j,k}$}$_{1\le i,j,k \le n}$, with $a_{i,j,k} \in [0,1]$, and the two …

Debapratim Banerjee, Matteo Sordello

PDF DOI

Clustering dynamics in a class of normalised generalised gamma dependent priors

Normalised generalised gamma processes are random probability measures that induce nonparametric prior distributions widely used in …

Matteo Ruggiero, Matteo Sordello

PDF DOI

Robust Learning Rate Selection for Stochastic Optimization Using Splitting Diagnostic

This paper proposes SplitSGD, a new stochastic optimization algorithm with a dynamic learning rate selection rule. This procedure …

Matteo Sordello, Weijie Su

PDF Slides

See all publications

Talks

ICLR 2021 Workshop on Distributed and Private Machine Learning Contributed Talk on Privacy Amplification via Iteration for Shuffled and Online PNSGD
JSM 2020 in Philadelphia, Pennsylvania, USA. (remote) Session in Statistical Learning and Data Science
Welcome Home 2019 in Torino, Italy, organized by the Math Department Giuseppe Peano.
JSM 2019 in Denver, Colorado, USA. Invited Session in Uncertainty Quantification for Stochastic Optimization Methods in Machine Learning
JSM 2018 in Vancouver, Canada. Session in Model-Based Statistics and Applications
Welcome Home 2017 in Torino, Italy, organized by the Math Department Giuseppe Peano.

Matteo Sordello

PhD Student in Statistics

Wharton School, UPenn

Biography

Interests

Education

Publications

Privacy Amplification via Iteration for Shuffled and Online PNSGD

A Test for Differential Ascertainment in Case-Control Studies with Application to Child Maltreatment

A Bernstein type inequality for sums of selections from three dimensional arrays

Clustering dynamics in a class of normalised generalised gamma dependent priors

Robust Learning Rate Selection for Stochastic Optimization Using Splitting Diagnostic

Talks

Skills

Statistics

Python

R

Data Analysis

Volleyball

Table Tennis