Changelog & News

This page is a changelog & news for my website (reverse chronological).

2024

• October 1: Jean-Jacques Godeme is joining me as a postdoc to work on automatic differentiation. Welcome!
• September 26: Just learned that I will be a 3IA chair holder for the next 4 years for my project BOGL (Bilevel Optimization for Graph Learning).
• September 26: Our (w/ F. Iutzeler & E. Pauwels) paper Derivatives of Stochastic Gradient Descent was accepted to NeurIPS 2024. _ September 23-25: We organized with L. Calatroni the LOCA workshop in Sophie-Antipolis. _ September 10: I gave a talk at the Statistical and Probabilistic Analysis of Random Networks and Processes conference.
• September 2: Started my tweet serie "One Piece of Math a Day" on Twitter. Also available on my website here.
• July 9: I gave a talk at Inria Grenoble on automatic differentiation.
• July 1-3: Attending EURO 2024. I will give an invited talk in the "Algorithms for machine learning and inverse problems" session.
• June 27: The grant ANR PRC MAD was just accepted. I will be the PI of the project "Mathematics of Automatic Differentiation" for the next 4 years with the following consortium: J. Bolte, S. Gadat, E. Pauwels (Toulouse School of Economics), G. Fort, F. Iutzeler (Université Paul Sabatier) and J.-B. Caillau, Y. Laguel (Université Côte d'Azur).
• June 23-30: Visiting G. Gidel at MILA. I gave a talk at MTL Opt.
• June 15: Accepted paper to TMLR with Hashem Ghanem and Nicolas Keriven Gradient Scarcity with Bilevel Optimization for Graph Learning with Featured Certification!
• May 28: New preprint with Sophie Jaffard and Patricia Reynaud-Bouret CHANI: Correlation-based Hawkes Aggregation of Neurons with bio-Inspiration.
• May 21: New preprint with Franck Iutzeler and Edouard Pauwels on the Derivatives of Stochastic Gradient Descent.
• 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. I presented our work on iterative automatic differentiation.
• 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.