Gilles Bareilles
Scholar

Gilles Bareilles

Google Scholar ID: QCXtXe8AAAAJ
Post-doc at the Czech Technical University in Prague
OptimizationMachine Learning
Citations & Impact
All-time
Citations
80
 
H-index
3
 
i10-index
2
 
Publications
15
 
Co-authors
0
 
Resume (English only)
Academic Achievements
  • - Publications:
  • - Accepted at Neurips Constrained Optim for ML workshop: Benchmark of solvers for learning with constraints
  • - Accepted at Neurips: Work on generalization and monotonicity in preference learning
  • - Awards:
  • - Received the 'Prix Dodu' award for one of the three best talks among young researchers at Journées MODE
  • - Talks:
  • - September 2025: Neurips Constrained Optim for ML workshop
  • - September 2025: Neurips conference
  • - June 2023: FOCM conference poster presentation
  • - December 2022: Inria Mind seminar
  • - December 2022: PhD defense
  • - November 2022: Rutgers Optim & ML seminar
  • - October 2022: Inria MLSP seminar
  • - October 2022: Journées MOA
  • - June 2022: CANUM
  • - June 2022: Journées MODE
  • - December 2020: LJK PhD day
  • - September 2020: Journées MODE virtual conference
  • - February 2020: ROADEF conference
Research Experience
  • - Postdoctoral fellow at CTU (Prague) in the optimization group, working with Jakub Mareček on the optimization of tame functions.
  • - Previously, conducted PhD research in the DAO team at Laboratoire Jean Kuntzmann (Grenoble).
Education
  • - PhD:
  • - University: Laboratoire Jean Kuntzmann (Grenoble)
  • - Advisors: Franck Iutzeler and Jérôme Malick
  • - Time: Until December 2022
  • - Specialization: DAO team, focusing on structured nonsmooth problems
Background
  • - Research Interests: Machine learning; Nonsmooth nonconvex optimization; Second-order methods; Riemannian optimization.
  • - Professional Field: Optimization algorithms
  • - Introduction: Postdoctoral fellow at CTU (Prague), in the optimization group, working with Jakub Mareček on the optimization of tame functions. As of November 2025, will join El Mahdi El Mhamdi's team on the robustness of preference learning methods.
Miscellany
  • - Personal Interests: Not provided
Co-authors
0 total
Co-authors: 0 (list not available)