Rianne de Heide
 |
Machine Learning Group, Statistical Science Group |
About me
I am a postdoc at the Institut für Mathematische Stochastik (IMST), Fakultät für Mathematik (FMA) in the Otto von Guericke Universität in Magdeburg, where I work with Alexandra Carpentier. My position is funded by the Leiden IBM-SPSS fund, hence my affiliation with Leiden University, where I (remotely) work with Jacqueline Meulman on the IBM-SPSS project.
I work on problems and solutions in machine learning and statistics. My research focuses on sequential learning, and in particular on (sequential) hypothesis testing, Bayesian learning and bandit problems. I am interested in exploring the limitations of existing methods under misspecification of the model or the data collecting process, and in devising new, robust methods for these settings. I’m also interested in the mathematical and philosophical foundations of Bayesianism, machine learning, statistics and probability theory.
Previously
My PhD research was carried out at the Centrum Wiskunde & Informatica (CWI, the national research institute for mathematics and computer science in the Netherlands), in the Machine Learning group, under supervision of Peter Grünwald. This work resulted in my dissertation Bayesian Learning: Challenges, Limitations and Pragmatics, which got me my PhD from Leiden University. My promotores were Peter Grünwald and Jacqueline Meulman, and my co-promotor was Wouter Koolen. My PhD position was funded by the Leiden IBM-SPSS fund.
From April till August 2019, I visited SequeL (now SCOOL) at Inria Lille-Nord Europe on a LUF travel grant, to work with Emilie Kaufmann and Michal Valko.
Until August 2020 I was a board member of the European Women in Mathematics – The Netherlands, the Dutch association of women professional mathematicians.
Until January 2019 I worked one day a week at Leiden University with Jacqueline Meulman as coordinator of the MSc programme Statistical Science.
I obtained a BSc in Mathematics from the University of Groningen and a MSc in Mathematics cum laude (with honours) from Leiden University. I also hold a Bachelor of Music from the Prins Claus Conservatoire and a Master of Music from the Royal Conservatory of The Hague, both in Classical music - Horn.
Research
My research interests include
Bandits, Reinforcement Learning
(Sequential) hypothesis testing
Group invariance in statistics
Bayesian methods
Learning theory
Foundations of ML, stats and probability theory
Recent Publications
The truth-convergence of open-minded Bayesianism
Tom F. Sterkenburg and Rianne de Heide
The Review of Symbolic Logic 2021, 1-38. doi:10.1017/S1755020321000022 philsci archive procOptional Stopping with Bayes Factors: A Categorization and Extension of Folklore Results, with an Application to Invariant Situations
Allard Hendriksen, Rianne de Heide and Peter Grünwald
Bayesian Analysis 2021, doi:10.1214/20-BA1234. arxiv procWhy optional stopping can be a problem for Bayesians
Rianne de Heide and Peter Grünwald
Psychonomic Bulletin & Review 2020, doi:10.3758/s13423-020-01803-x proc
Extended technical report: arXiv 1708.08278