My main research is on numerical optimization: theory, algorithms, and applications. I am currently focusing on efficient methods (both deterministic and stochastic) for convex optimization and nonconvex optimization, with applications in machine learning, control, signal/image processing, engineering, and data science.
Currently I am a postdoctoral researcher at university of Helsinki, Finland, working in the department of Mathematics and Statistics with Tuomo Valkonen.
Area of intrerest:
I am broadly interested in exploring the following areas:
- Optimization: Theory and algorithms with a focus on structure exploitation, sparsity, convexity, stochasticity, and low-rank optimization.
- Development of efficient methods for convex and non-convex problem classes, including smooth and nonsmooth formulations.
- Second-order and higher-order optimization methods.
- Online optimization with a specific interest in bilevel optimization settings.
I defended my Ph.D thesis in May, 2024 supervised by Ion Necoara within the Marie Skłodowska-Curie early stage research, TraDE-Opt project as ESR 10. My thesis is “Higher-order methods for composite optimization and applications”.
I received a BSc degree in Applied Mathematics from University Cadi Ayyad in 2016. I obtained a MSc degree in Applied mathematics from Faculty of Science and Technology, Morocco in 2018.
Publications:
- Yassine Nabou, Ion Necoara, Regularized higher-order Taylor approximation methods for composite nonlinear least-squares, arxiv 2024.
- Yassine Nabou, Ion Necoara, Moving higher-order Taylor approximations method for smooth constrained minimization problems, arxiv, 2024, (pdf).
- Yassine Nabou, Francois Glineur, and Ion Necoara, Proximal gradient methods with inexact oracle of degree q for composite optimization, Optimization Letters, 2024, (pdf).
- Yassine Nabou, Ion Necoara, Efficiency of higher-order algorithms for minimizing composite functions, Computational Optimization and Applications, 2024, (pdf).
- Yassine nabou, Lucian Toma, and Ion Necoara, Modified projected Gauss-Newton method for constrained nonlinear least-squares: application to power flow analysis, European Control Conference 2023, (pdf).
Talks:
- October 31, 2024: Higher-Order Methods for Composite Optimization with Application, MOP Research Seminar, Saarland University, Germany, online.
- September 16, 2024: Efficient Algorithms for composite problems with applications, ESAT KU Leuven, Belgium, invited by Hakan Ergun, online.
- January 23-26, 2024: Moving higher-order Taylor approximations method for smooth constrained minimization problems, Workshop on Analysis and Potential, website, Bucharest, Romania.
- September 29-30, 2023: Moving higher-order Taylor approximations method for smooth constrained minimization problems, conference on statistical modeling with applications, website, Bucharst.
- July 4-8, 2022: Efficient optimization methods for complex systems, Workshop on Algorithmic and Continuous Optimization (website), UCLouvain, Belgium.
- August 24, 2021: Higher-order algorithms for composition minimization problems, MaLGa Machine Learning Genoa Center, Italy, invited by Silvia Villa, online.
Teaching experience:
-