The Polynomial Optimization chair is concerned with four main research directions:
- Develop efficient optimization algorithms in view of their application to help analyze and/or solve challenging hard problems in Machine Learning (ML).
A particular emphasis is on ad-hoc positivity certificates (based on linear/second-order/semidefinite programming) from real algebraic geometry to provide efficient scalable convex relaxations to hard non convex ML problems. - Data driven approach to control dynamical systems via a combination of Koopman operator and convex relaxations. For instance this approach can be used to determine the maximum positively invariant set from data.
- Stability and performance verification of dynamical systems controlled by neural networks using semialgebraic representation of nonlinearities and efficient positivity certificates. This allows one to search rigorous certificates of stability for dynamical systems controlled by neural networks trained from data.
- Promoting the Christoffel-Darboux (CD) kernel (and associated Christoffel function), as a powerful (and easy to use) tool from theory of approximation and orthogonal polynomials, largely ignored in analysis of (discrete) clouds of data points. It can be used to encode clouds of data points, to detect outliers, and for support inference as well.
Programs: Acceptable, certifiable & collaborative AI
Themes: Learning with little or complex data, optimization and game theory for AI, data and anomalies
Chair holder:
Jean-Bernard Lasserre, Directeur de recherche émérite, CNRS. Laas, Toulouse
Co-chairs:
- Milan Korda,co-chair: CNRS, LAAS Toulouse
- Victor Magron,co-chair: CNRS, LAAS Toulouse
Sites
- https://homepages.laas.fr/mkorda/
- https://homepages.laas.fr/vmagron/
- https://scholar.google.com/citations?user=WD6Z0XAAAAAJ&hl=zh-CN
.
Chair holder: Jean Bernard LASSERRE (CNRS, LAAS)
Co-chairs:
- Milan KORDA (CNRS, LAAS),
- Victor MAGRON (CNRS, LAAS)
PhD students
- TONG Chen (ANITI), October 2019 – September 2022
- Hoang Ngoc Anh Mai (EDMITT) October 2019 – September 2022
- Corbinian Shlosser (EDMITT) February 2020 -January 2023
Post-docs
- Jie Wang (ANR T-ERC COPS), July 2019 – June 2021
Visiting researchers
- Felix Kirschner, PhD (EU POEMA), Netherlands, March-June 2021
- Edgar Fuentes, PhD (EU POEMA), France, June-September 2021
- Vit Cibulka (Phd), Czech Republic, October 2020 – February 2021
- Nicolas Bauwens (Master), Belgium, March 2021 – June 2021
- Antonin Hurska (Master), Czech Republic, March 2020
- Europe : H2020 Marie Slodowska-Curie Training Network POEMA (Magron, M. Korda, J.-B. Lasserre)
- France: ANR T-ERC COPS (V. Magron)
- AMIES PEPS2 (J.-B. Lasserre, V. Magron)
- POPSIC CIMI-ANITI (V. Magron)
- CIMI (M. Korda)
- GACR 20-11626Y (M. Korda)
- Other: CREATE, Singapore (J.-B. Lasserre, M. Korda, V. Magron)
Jean-Bernard Lasserre received the Grand Prix Inria - Académie des sciences for his research work, particularly in mathematical optimization. Recognition of an exemplary scientific career, with major contributions and applications in many fields of science and engineering. Know more
- BrainPOP seminar
- CIMI-ANITI school on optimization
- French-German Machine Learning Symposium (May 2021)
- V. Magron and J. Wang. SONC Optimization and Exact Nonnegativity Certificates via Second- Order Cone Programming. Journal of Symbolic Computation, 2021.
- Wang Jie, Magron V., Lasserre J.B. (2021) TSSOS: A Moment-SOS hierarchy that exploits term sparsity, SIAM J. Optim 31(1), pp. 30–58
- Wang Jie, Magron V., Lasserre J.B. (2021) Chordal-TSSOS: A Moment-SOS hierarchy that exploits term sparsity with chordal extension, SIAM J. Optim 31(1), pp. 114—141
- Henrion D., Korda M., Lasserre J.B. The Moment-SOS Hierarchy: Lectures in Probability, Statistics, Computational Geometry, Control and non-linear PDEs, World Scientific, Singapore, 2020
- T. Chen, J.-B. Lasserre, V. Magron, and E. Pauwels. Semialgebraic Optimization for Bounding Lipschitz Constants of ReLU Networks, Proceeding of NeurIPS, 2021.
- Korda, M. Computing controlled invariant sets from data using convex optimization. SIAM J.Optim 58(5), 2871-2899, 2020.
- Cibulka, V., Korda, M., & Haniš, T. (2021). Spatio-Temporal Decomposition of Sum-of-Squares Programs for the Region of Attraction and Reachability. IEEE Control Systems Letters
- Lasserre J.B., Pauwels E., Putinar M. (2021) Christoffel-Darboux Kernel for Data Analysis, Cambridge University Press, UK. In press
- El Khadir B., Lasserre J.B., Sindhwani. Piecewise-Linear Motion Planning amidst Static, Moving, or Morphing Obstacles, IEEE International Conference on Robotics & Automation (ICRA 2021), Xi’an, China, May-June 2021
In AI too, we think global and act local - with Jean-Bernard Lasserre
For the mathematician Jean-Bernard Lasserre, every problem has a local, imperfect solution, and a global solution, the best absolutely. The researcher is testing global optimization methods in artificial intelligence. He also promotes the use of the mathematical function of Christoffel, for certain problems in data analysis.