Our research group is part of the School of Computer and Communication Sciences at EPFL in Lausanne, Switzerland. The group is lead by Matthias Grossglauser and Patrick Thiran. Our research focuses broadly on the statistical modeling of large dynamical systems involving both human and technical agents. Examples include social and information networks, epidemic processes, human mobility and transportation, and recommender systems. Our work lies at the intersection of machine learning, probabilistic modeling, large-scale data analytics, and performance analysis. Here are the research areas we work on:
Hierarchical Reinforcement Learning with Targeted Causal Interventions M. Khorasani, S. Salehkaleybar, N. Kiyavash and M. Grossglauser 42nd International Conference on Machine Learning, ICML 2025, Vancouver, 2025-07-13 - 2025-07-19.
Assessing the Performance of NOMA in a Multi-Cell Context: A General Evaluation Framework A. Bardou, J. M. Gorce and T. Begin IEEE Transactions on Wireless Communications, 1 - 1, 2025.
Almost exact recovery in noisy semi-supervised learning K. Avrachenkov and M. Dreveton Probability in the Engineering and Informational Sciences, 1 - 22, 2024.
Efficiently Escaping Saddle Points for Policy Optimization M. Khorasani, S. Salehkaleybar, N. Kiyavash, N. He and M. Grossglauser 41th Conference on Uncertainty in Artificial Intelligence (UAI 2025), Rio de Janiro, Brazil, 2025-07-21-2025-07-26.
Universal Lower Bounds and Optimal Rates: Achieving Minimax Clustering Error in Sub-Exponential Mixture Models M. Dreveton, A. Gözeten, M. Grossglauser and P. Thiran The 37th Annual Conference on Learning Theory, Edmonton, Canada, 2024-06-30 - 2024-07-03.
We are hiring postdocs and PhD students in all our research areas.