This is the website of Samuel Vaiter. I am a CNRS researcher at the interface of mathematics and computer science. My current host lab is the Laboratoire J. A. Dieudonné of Université Côte d’Azur located in the beautiful city of Nice.

My research interests cover in particular the mathematical foundation of machine learning, especially linked to optimization. In particular, I work on graph machine learning, algorithmic differentiation, (stochastic ∨ bilevel ∨ nonsmooth) optimization. I am currently an Area Chair for NeurIPS, ICML, ICLR and AISTATS.

Previously, I was a member of Institut de Mathématiques de Bourgogne, located in the city of Dijon, France during 2015-2021 and a postdoc at CMAP, the applied math institute of École Polytechnique with Antonin Chambolle during the academic year 2014-2015. Before that, I did my PhD at CEREMADE (Univ. Paris-Dauphine) under the supervision of Gabriel Peyré. More information are available on my About page.

Open Positions

• Master 2 internship Adaptive methods for safe machine learning (location: Nice) with Yassine Laguel.
• Master 2 internship Interplay between stochastic algorithms and automatic differentiation (location: Toulouse) with Edouard Pauwels.
• Master 2 internship/PhD A learning theory for over-parametrized bilevel optimization (location: Grenoble) with Michael Arbel and Edouard Pauwels.
• Postdoc (24 months) Automatic differentiation and control (location: Nice). Filled.
• Master 2 internship/PhD Bilevel learning of hyper-parameter estimation in image reconstruction problems (location: Genova/Nice) with Luca Calatroni. Filled.

News

• April 9: Our blogpost with Mathieu Dagréou, Pierre Ablin and Thomas Moreau How to compute Hessian-vector products? was accepted to ICLR 2024 as spotlight.
• March 1-9: Visiting A. Bietti at CCM, Flatiron Institute, NYC.
• January 24: Talk at the kickoff meeting of the PEPR PDE-AI project.
• January 20: Our papers Provable local learning rule by expert aggregation for a Hawkes network and A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization were accepted to AISTATS 2024.

Current PhD students for 2024/2025

• Sophie Jaffard (2022-2025?), co-supervised with Patricia Reynaud-Bouret;
• Matthieu Cordonnier (2021-2024?), co-supervised with Nicolas Keriven and Nicolas Tremblay;
• Mathieu Dagréou (2021-2024?), co-supervised with Thomas Moreau and Pierre Ablin;

Current teaching

• SMEMI306 - ECUE: Modeling Studies @Université Côte d’Azur

Contact:
Samuel Vaiter
Laboratoire Mathématiques & Interactions J.A. Dieudonné
CNRS UMR 7351, Université Côte d’Azur
Parc Valrose 06108 NICE CEDEX 2, France
mail: samuel.vaiter@cnrs.fr
github: @svaiter, twitter: @vaiter