Optimal transport for
machine learning & domain adaptation

Exploring how optimal transport provides a mathematical framework for developing machine learning methods that generalize across domains, with applications in genetics and life sciences.

DISCOVER MY RESEARCH

About

Associate Professor, Paris Cité University

Qualification CNU sections 26, 27 and 61

mourad.el-hamri [AT] u-paris.fr

4 Av. de l’Observatoire, 75006 Paris, France

I am an Associate Professor at Paris Cité University, affiliated with the BioSTM Laboratory and the Faculty of Pharmacy. My work explores how machine learning systems can better adapt to changing environments and tasks, drawing inspiration from the remarkable flexibility of the brain. This line of research is rooted primarily in domain adaptation and transfer learning, with a particular emphasis on Optimal Transport theory as a geometric framework for modeling, computation, and theoretical guarantees.

More recently, I have developed a strong interest in applications to genetics and, more broadly, the life sciences, where these methods can help uncover the structure and complexity of biological processes through data-driven models.

Prior to this position, I served as an Assistant Professor at Sorbonne Paris Nord University, where I also received my PhD and Master’s degree in Machine Learning. My earlier training was in Applied Mathematics, with both Bachelor’s and Master’s degrees from the Faculty of Sciences in Fez, Kingdom of Morocco.

Read more
Mourad El Hamri

Latest News

January 2026

Paper presentation at AAAI-26 (Singapore): Theoretical Guarantees for Domain Adaptation with Hierarchical Optimal Transport.

December 2025

Paper accepted in ACS Applied Bio Materials: Machine Learning for the Prediction of Size and Encapsulation Efficiency of mRNA-Loaded Lipid Nanoparticles.

November 2025

Open M2 internship position with Marie Verbanck: Genetics Guided Optimal Transport for Integrative Validation of Complex Trait Associations.