El Mahdi Chayti is a Ph.D. candidate in Machine Learning at the École Polytechnique Fédérale de Lausanne (EPFL), under the supervision of Prof. Martin Jaggi at the Machine Learning and Optimization Laboratory (MLO). His research focuses on optimization methods for large-scale machine learning, with particular interests in collaborative optimization, non-convex stochastic optimization, second-order methods, and bi-level optimization.

He holds engineering degrees from École Polytechnique and ENSTA ParisTech, as well as a Master’s degree in Data Science from École Polytechnique and Paris-Saclay University, all awarded with high honors. Prior to joining EPFL, he conducted research at institutions including EDF, Airbus, CERFACS, and MILA (Montréal), where he worked on topics such as Bayesian deep learning, generative modeling, and physics-informed neural networks.

His research has been published in leading venues such as ICML, ICLR, AISTATS, and TMLR. He also serves as a reviewer for major conferences and journals including NeurIPS, ICML, ICLR, and JMLR, and contributes to teaching activities within the School of Computer and Communication Sciences at EPFL.

 El Mahdi Chayti’s research focuses on optimization for machine learning and the theoretical foundations of learning algorithms. His work explores stochastic, second-order, and collaborative optimization methods, aiming to improve the efficiency and theoretical understanding of large-scale learning systems. 

 El Mahdi Chayti has served as a teaching assistant in several courses at EPFL, including Machine Learning (CS-433), Optimization for Machine Learning (CS-439), Deep Learning in Biomedicine (CS-502), and Object-Oriented Programming in Java (CS-108). He has also contributed to laboratory courses in data science. His teaching interests span machine learning, optimization, and applied data science, with a focus on fostering strong theoretical understanding and practical implementation skills among students.