STATISTICAL METHODOLOGY

PUBLICATIONS

Missing Value Imputation in Relational Data using Variational Inference
In real-world networks, node attributes are often only partially observed, necessitating imputation to support analysis or enable …
Simon Fontaine, Jian Kang, Ji Zhu
May, 2025 JCGS Misc
Code Project DOI
An adaptive multiple try Metropolis algorithm
Markov chain Monte Carlo (MCMC) methods, specifically samplers based on random walks,often have difficulty handling target …
Simon Fontaine, Mylène Bédard
August, 2022 Bernoulli Misc
PDF Cite Code DOI Paper code Supplementary material
A Unified Approach to Sparse Tweedie Modeling of Multisource Insurance Claim Data
Actuarial practitioners now have access to multiple sources of insurance data corresponding to various situations: multiple business …
Simon Fontaine, Yi Yang, Wei Qian, Bowen Gu, Bo Fan
January, 2020 Technometrics Misc
PDF Cite Code DOI Supplementary material

WORKING PAPERS

Bayesian Fréchet Regression
Fréchet regression is a statistical method that extends traditional regression to model responses in metric spaces by minimizing the …
Simon Fontaine, Lingzhou Xue, Bing Li
October, 2025 In Preparation Misc
Code Project

THESES

Statistical Models for Dependent Data
Dependency among observations can arise from a multitude of sources, including spatial or temporal correlation, grouped, clustered or …
Simon Fontaine
June, 2024 PhD thesis, University of Michigan Misc
PDF Cite
MCMC adaptatifs à essais multiples
This memoir aims at introducing adaptation within the Multiple-Try Metropolis (MTM) algorithms which are a special case of the Markov …
Simon Fontaine
January, 2019 Master’s thesis, University of Montreal Misc
PDF Cite

TALKS

Bayesian Fréchet Regression
While linear regression focuses on studying the relationship between a set of covariates and a real-valued response, Fréchet regression …
Jun 15, 2025 10:00 AM ICSA 2025 Storrs, CT, USA
Simon Fontaine, Lingzhou Xue, Bing Li
Missing Value Imputation of Network Node Attributes
User profiles in social networks are notoriously incomplete due to self-reporting; predicting or imputing these missing values is often …
Aug 10, 2021 10:00 AM JSM 2021 Online
Simon Fontaine, Ji Zhu
Slides
Online Skill Rating Algorithms
Skill rating algorithms are now ubiquitous in online competitive video games and are used not only to accurately compare players’ …
Aug 1, 2019 8:30 AM JSM 2019 Denver, CO, USA
Nicolas Grenon-Godbout, Jonathan Dumas, Simon Fontaine, Gabrielle Rit, Timothy Park

COURSE WORK & REPORTS

U.S. Mortality 2007-2018: Identifying Trends and Patterns in Mortality Trajectories
Simon Fontaine
May, 2020 Course Work
PDF Code
A proximal alternating direction method for regularized multi-task regression
We propose an alternating direction of multipliers method (ADMM) based on the consensus scheme for solving regularized multi-task …
Simon Fontaine, Jinming Li, Yang Li
January, 2020 Course Work
PDF Code
Caught Looking: Analyzing Variation in Umpire Strike Zones
As technology advances, Major League Baseball (MLB) has faced increased pressure from fans, coaches, and players to use video …
Simon Fontaine, Moritz Korte-Stapff, Brian Manzo
January, 2020 Course Work
PDF Code Slides
Latent Variable Modeling of Paired Comparisons with Application to NCAA Men’s Basketball Score
We propose a latent variable model for paired comparisons in the context of Basketball scores. Based on the model proposed by [1], our …
Simon Fontaine
January, 2020 Course Work
PDF Code Slides
MovieLens Datasets—Predicting and Analyzing User Ratings of Movies
The MovieLens datasets contain user ratings of movies as well as movie and user information. In this report, we consider four …
Simon Fontaine, Trong Dat Do
January, 2020 Course Work
PDF Code Slides