I work on optimization methods for nonsmooth structured problems, which include learning problems and more general nonsmooth problems. Currently, I'm interested in fast Newton-type methods for nonsmooth problems, and structure identification with and without proximal operator.
I'm also in charge of the team's reading group.
Interests: Machine learning; Nonsmooth optimization; Second-order methods; Riemannian optimization
December 2022: Newton methods for structured nonsmooth optimization, Inria Mind seminar, Saclay (online).
December 2022: I defended my PhD on December 2nd, 2022. I was very happy to have in the jury: Jalal Fadili and Claudia Sagastizábal as rapporters, Jean-Charles Gilbert and Mathurin Massias as examiners, and Nadia Brauner as president. Claude Lemaréchal also attended! Manuscript & Slides
November 2022: Newton methods for structured nonsmooth optimization, Rutgers Optim & ML seminar (online).
October 2022: Newton methods for structured nonsmooth optimization, Inria MLSP seminar, Lyon.
October 2022: Newton methods for nonsmooth composite optimization, Journées MOA, Nice, Slides.
December 2020: Harnessing Structure in Optimization for Large-scale Learning, LJK PhD day, Grenoble.
Laboratoire Jean Kuntzmann
Bâtiment IMAG - Bureau 164 - Domaine Universitaire
38400 Saint Martin d'Hères
E-mail: firstname . lastname |a|_ univ-grenoble-alpes.fr