Nicolas Flammarion

Editer le profil

nicolas.flammarion@epfl.ch +41 21 693 27 37 https://scholar.google.com/citations?user=7nVGYfgAAAAJ&hl

EPFL IC IINFCOM TML
INJ 336 (Bâtiment INJ)
Station 14
1015 Lausanne

+41 21 693 27 37
+41 21 693 52 26
Local: INR 110
EPFL > IC > IINFCOM > TML

+41 21 693 27 37
EPFL > IC > IC-SSC > SSC-ENS

Web site: Site web: https://ssc.epfl.ch

+41 21 693 27 37
EPFL > VPA-AVP-DLE > AVP-DLE-EDOC > EDIC-GE

Web site: Site web: https://go.epfl.ch/phd-edic

vCard
Données administratives

Biographie

Nicolas Flammarion is a tenure-track assistant professor in computer science at EPFL. Before that, he was a postdoctoral fellow at UC Berkeley, hosted by Michael I. Jordan. He received his PhD in 2017 from Ecole Normale Superieure in Paris, where he was advised by Alexandre d’Aspremont and Francis Bach. In 2018, he received the prize of the Fondation Mathématique Jacques Hadamard for the best PhD thesis in the field of optimization, in 2021, he was one of the recipients of the NeurIPS Outstanding Paper Award, and in 2024, he received a Trust & Safety Google Research Award. 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.

Complete CV

Enseignement & Phd

Enseignement

Computer Science

Communication Systems

Doctorants

D'Angelo Francesco, Papazov Hristo Georgiev, Varre Aditya Vardhan, Yüce Gizem, Yüksel Oguz Kaan,

A dirigé les thèses EPFL de

Andriushchenko Maksym , Pesme Scott William , Vladarean Maria-Luiza ,

Cours

Machine learning

Les méthodes de l'apprentissage automatique deviennent de plus en plus importants dans de nombreuses sciences et applications. Dans ce cours, les principes fondamentaux et les méthodes d'apprentissage automatique seront introduits, analysés et pratiquement mis en œuvre.

Optimization for machine learning

Ce cours donne un aperçu des méthodes d'optimisation modernes, pour les applications dans l'apprentissage automatique et la science des données. En particulier, l'évolutivité des algorithmes vers de grands ensembles de données sera discutée en théorie et en mise en œuvre.