Sébastien Colla

_images/seb.JPG

Ph.D. student
FRIA Research fellow

INMA - Mathematical Engineering Department
ICTEAM - Institute of Information and Communication Technologies, Electronics and Applied Mathematics
UCLouvain - Université Catholique of Louvain
My advisor is Julien Hendrickx
Quick links | scholar_logo Google Scholar | GitHub | linkedin_logo Linkedin

News

  • I have presented my first conference paper to the 60th Conference on Decision and Control (2021)!
    Sebastien Colla, Julien M. Hendrickx, “Automated Worst-Case Performance Analysis of Decentralized Gradient Descent”, in 60th IEEE Conference on Decision and Control (CDC), 2021. [PDF, slides, video]
  • We have extended the PESTO toolbox to make our results easy to use by anyone that would like to analyze worst-case performance of decentralized algorithms.

Research Interests

  • Decentralized Optimization
  • Computer-aided worst-case analyses
  • Multi-Agent system.

The goal of my thesis is to boost the research in decentralized optimization by creating tools allowing one to automatically compute the worst-case performance of any decentralized optimization algorithm, and to identify the bottleneck instances, providing insight on what limits the performance. This will contribute to a better understanding of decentralized optimization algorithms and enable rapid exploration of new algorithms ideas and their iterative improvement.

This project relies on the Performance Estimation Problem (PEP) approach developed by Adrien Taylor for classical centralized optimization during his thesis. It relies on formulating the evaluation of an algorithm worst-case performance as an optimization problem itself, whose variables are the objective functions and initial conditions. Such problems are very complex, but have been shown to be solvable exactly. The PESTO toolbox allows to write and solve them easily.

Here is a Vulgarized Summary of my research project.