Regular biography
Lénaïc Chizat is a Tenure Track Assistant Professor in the Department of Mathematics at École Polytechnique Fédérale de Lausanne. His research focuses on computational optimal transport and machine learning, with an emphasis on mathematical analysis of supervised learning techniques and artificial neural networks. He teaches courses such as Computational Optimal Transport and Topics in Machine Learning. Chizat is affiliated with the DOLA laboratory and holds an office in Building MA, Room C2 657. His contact information is lenaic.chizat@epfl.ch, and his website is https://people.epfl.ch/lenaic.chizat?lang=en.
Scholar-generated biography
Lénaïc Chizat is a researcher specializing in Optimization, Machine Learning, Optimal Transport, and Algorithms. His work focuses on the theoretical and algorithmic aspects of optimization in machine learning, particularly in the context of optimal transport and its applications. He has contributed to understanding the global convergence of gradient descent for over-parameterized models, the implicit bias of gradient descent in neural networks, and the development of efficient algorithms for unbalanced optimal transport problems. His research also explores the statistical and topological properties of probability divergences and the convergence of mean-field Langevin dynamics. Chizat's publications highlight the interplay between optimization, statistics, and machine learning, with a strong emphasis on theoretical foundations and practical algorithms.