Clément W. Royer
La version française de cette page se trouve ici.
Lectures
Optimization for Machine Learning
CIMPA school "Control, Optimization and Model Reduction in Machine Learning", February 2025.
See
dedicated webpage.
Complexity in continuous optimization
Lectures for Dauphine's Computer Science PhD track, February-March 2025.
Lecture 1: Gradient descent and Newton on nonconvex problems
Slides Board
Lecture 2: Accelerated gradient from convex to nonconvex
Board
Lecture 3: Second-order methods and guarantees
Board
Lecture 4: Complexity and stationary points
Board
Lecture 5: High-order methods
Board
Lecture 6: Complexity and linear programming
Board
Selected talks
Derivative-free optimization using subspacesSlides
SMAI-MODE Days, 2024, Lyon, France.
SIAM Conference on Optimization, 2023, Seattle, WA, USA.
University of Michigan's MIDAS seminar, 2022, Ann Arbor, MI, USA.
Lehigh University ISE seminar, 2022, Bethlehem, PA, USA.
Newton-Conjugate Gradient methods with complexity guarantees
Slides
CAS Seminar, Mines Paris-PSL school, 2023.
Computational Maths Seminar, Australian National University (Canberra, Australia), 2021, online.
ICML Workshop "Beyond first-order methods in ML systems", 2021, online.
Stochastic Levenberg-Marquardt algorithms for nonlinear least squares and data assimilationSlides
Workshop on Advances in Continuous Optimization (EUROPT), 2021, online (originally in Toulouse, France).
SIAM Conference on Computational Science and Engineering, 2021, online (originally planned in Forth
Worth, TX, USA).
A complete list of my talks and posters is available in my
vitae.
Materials on this page are available under Creative Commons
CC BY-NC 4.0 license.