Research Fellow in Optimization-driven hybrid AI (DesCartes – WP3)

The DesCartes programme is developing a hybrid AI, combining Learning, Knowledge and Reasoning, which has good properties (need for less resources and data, security, robustness, fairness, respect for privacy, ethics), and demonstrated on industrial applications of the smart city (digital energy, monitoring of structures, air traffic control).

The program brings together 80 permanent researchers (half from France, half from Singapore), with the support of large industrial groups (Thales SG, EDF SG, ESI group, CETIM Matcor, ARIA etc.).

The research will take place mainly in Singapore, at the premises of CNRS@CREATE, with a competitive salary and generous funding for missions.

Read more about the DesCartes program here.

WP3 aims at

supporting the whole Descartes program in order to develop advanced optimization-based solutions in the context of hybrid AI. Any AI system or machine learning algorithm ultimately involves a formulation with an objective or loss function to be minimized. The modelling of the problem as well as the chosen objective function optimization algorithm is crucial to the success of the overall AI task. This is all the more crucial in the context of hybrid AI, which seeks to integrate physics-inspired models with machine learning algorithms. We will address this problem from two complementary angles, namely optimization-based methods and machine learning-based methods.

The goal of this postdoctoral position is to solve robust polynomial optimization. The traditional setting uses deterministic uncertainty sets (i.e., neither distributional, nor data-driven). The postdoctoral fellow will consider data-driven distributionally robust optimization, will examine various distributional uncertainty sets, and will also rely on parametric polynomial optimization. Evolutionary algorithms will also be evaluated for solving these robust optimization problems.

Competences in some of the domains listed below will be highly considered:

• Computer Science
• Optimization
• Machine Learning.

Keywords:

1. Optimal power flow
2. Optimization (convex, non convex)
3. Deep learning
4. Programming (python or Julia or Matlab)