⌘
— Preprint: Derivatives of SGD
New preprint with Franck Iutzeler and Edouard Pauwels on the Derivatives of Stochastic Gradient Descent.
New preprint with Franck Iutzeler and Edouard Pauwels on the Derivatives of Stochastic Gradient Descent.
Our blogpost with Mathieu Dagréou, Pierre Ablin and Thomas Moreau How to compute Hessian-vector products? was accepted to ICLR 2024 as spotlight.
Visiting A. Bietti at CCM, Flatiron Institute, NYC. I presented our work on iterative automatic differentiation.
Talk at the kickoff meeting of the PEPR PDE-AI project.
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.