Regular biography
Nicolas Flammarion is a tenure-track assistant professor in computer science at École Polytechnique Fédérale de Lausanne. He received his PhD in 2017 from École Normale Supérieure in Paris, where he was advised by Alexandre d'Aspremont and Francis Bach. Before joining EPFL, he was a postdoctoral fellow at UC Berkeley, hosted by Michael I. Jordan. His research focuses on learning problems at the intersection of machine learning, statistics, and optimization. He aims to develop algorithmic and theoretical tools that improve our understanding of machine learning and increase its robustness and usability.
Scholar-generated biography
Nicolas Flammarion is a researcher specializing in Machine Learning, Optimization, and Statistics. His work focuses on adversarial attacks, robustness benchmarks, and the theoretical foundations of optimization algorithms. He has contributed to understanding the effectiveness of adversarial training, the implicit bias of stochastic gradient descent, and the convergence rates of optimization methods. His research also explores the relationship between sharpness and generalization, as well as variance reduction techniques for stochastic gradient Monte Carlo methods. Flammarion's publications emphasize query-efficient attacks, robustness benchmarks for large language models, and the theoretical analysis of gradient-based methods in machine learning.