codes — see my github profile. The python package PEPit for numerical worst-case analyses is available here and its documentation here.

talks — here is a selection of slides from previous presentations:

  • 07/2022: PEPit: a python package for worst-case analysis of first-order optimization methods and their continuous versions, ICCOPT, (slides)
  • 11/2021: Vers une IA plus frugale, talk at IHP for the IAPlusK seminar


  1. preprint
    Geometry-dependent matching pursuit: a transition phase for convergence on linear regression and LASSO
    Céline Moucer, Adrien Taylor, and Francis Bach


  1. journal
    PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python
    Baptiste Goujaud, Céline Moucer, François Glineur, Julien Hendrickx, Adrien Taylor, and Aymeric Dieuleveut
    Mathematical Programming Computation (to appear) 2024
  2. journal
    A systematic approach to Lyapunov analyses of continuous-time models in convex optimization
    Céline Moucer, Adrien Taylor, and Francis Bach
    SIAM journal on Optimization 2023