Intro Hi! I'm an ELLIS PhD student at the Amsterdam Machine Learning Lab supervised by Eric Nalisnick and Dan Zhang.

Research Interests Generally speaking, I'm interested in probabilistic modelling, sequential settings and generalization. My current research focuses on probabilistic modelling of non-stationary data. In this context, I worked on deep sequence models for continuous time and unsupervised adaptation under distribution shifts. Despite that, I'm also interested in ML - and probabilistic modelling in particular - for applications in Social Science.

Bio I graduated with a joint Master's in statistics from the Technical University Berlin and Humboldt University Berlin. I wrote my Master's thesis on continuous-time modeling under the supervision of Maja Rudolph at the Bosch Center for Artificial Intelligence. I spent some time in France, where I obtained a French engineering degree in applied mathematics and economics from ENSAE. In my Bachelor’s, I studied economics and political science at Humboldt University Berlin and the University of Munich.

I'm open to collaborations, feel free to reach out!

Publications

STAD
Test-Time Adaptation with State-Space Models
Mona Schirmer, Dan Zhang, Eric Nalisnick
Preprint
DivDis
Beyond Top-Class Agreement: Using Divergences to Forecast Performance under Distribution Shift
Mona Schirmer, Dan Zhang, Eric Nalisnick
DistShift Workshop @ NeurIPS 2023
EconBERTa
EconBERTa: Towards Robust Extraction of Named Entities in Economics
Karim Lasri, Pedro Vitor Quinta de Castro, Mona Schirmer, Luis Eduardo San Martin, Linxi Wang, Tomáš Dulka, Haaya Naushan, John Pougué-Biyong, Arianna Legovini, Samuel Fraiberger
EMNLP Findings 2023
CRU
Modeling Irregular Time Series with Continuous Recurrent Units
Mona Schirmer, Mazin Eltayeb, Stefan Lessmann, Maja Rudolph
ICML 2022