Céline Moucer

2 rue Simone Iff

75012 Paris, France

Office C406 (on floor 4)

celine[dot]moucer[at]inria[dot]fr

I am a second year PhD student at Inria Paris, under the supervision of Adrien Taylor and Francis Bach.

My research focuses on first-order convex optimization methods for machine learning problems (recently on coordinate descent). Previously, I have been working on continuous-time models related to these methods, using computer-aided techniques for worst-case analysis.

Prior to that, I graduated from Ecole Polytechnique (X2016) and got a master degree in Maths, Vision and Learning in 2020 (master MVA) from Ecole Normale Supérieure and Ecole des Ponts.

You can find a list of my publications and codes here.

news

Feb 14, 2023	PEP Talks took place à Louvain-la-Neuve, thanks to all the participants!
Oct 31, 2022	Registration for PEP talks opens!
Oct 24, 2022	During two days, we welcome 25 high school girls at INRIA Paris as part of the RJMI program.
Jul 25, 2022	Presenting PEPit at ICCOPT.
Sep 1, 2021	Starting my PhD at INRIA Paris.

selected publications

preprint

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

2022

Bib HTML PDF Code

@article{2022Goujaud,
  author = {Goujaud, Baptiste and Moucer, Céline and Glineur, François and Hendrickx, Julien and Taylor, Adrien and Dieuleveut, Aymeric},
  title = {PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python},
  year = {2022}
}

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 (to appear) 2023

Bib HTML PDF Code

@article{2022Moucer,
  author = {Moucer, Céline and Taylor, Adrien and Bach, Francis},
  title = {A systematic approach to Lyapunov analyses of continuous-time models in convex optimization},
  journal = {SIAM journal on Optimization (to appear)},
  year = {2023}
}