[EXTERNAL COURSE] Optimization algorithms for AI and learning algorithms for optimization problems
Abstract: This PhD course proposes to investigate the interaction of optimisation algorithms and theory with the practice of Artificial Intelligence (mainly Machine Learning models). The first part of the course reviews the different optimisation algorithms proposed in the literature to tune the parameters of Machine Learning models, the theoretical and empirical investigation of how and why such algorithms are successful even on very large scale models and how Bi-Level Optimisation is a (relatively new) tool which can help in solving advanced Machine Learning problems. The second part focuses on the use of Machine Learning and Data Mining tools to help solve Operations Research (i.e., combinatorial optimisation) problems and methods, such as Vehicle Routing, Travelling Salesman, Additive Manufacturing, and more complex decomposition strategies and problems. This part is structured as a review on the effectiveness of different learning models over various aspects of optimization: from the building of good heuristic solutions and the prediction of their quality, to the analysis of problems and structure of their instances to evince important properties. Finally, the third part examines some applications of predictive and prescriptive analytics in the challenging field of healthcare delivery.
Tentative schedule: The lectures consist of 24 hours divided between the three themes previously described (respectively 10h/10h/4h) and will take place on Friday mornings between 8:30am and 12:30am on the following dates: 17th and 24th of April, 8th, 15th, 22nd and 29th of May 2026 in streaming.
For more detail please refer to the document below.
Remember that in addition to the planned ah-courses (Ad-hoc Courses – Doctoral Program in ICT), our PhD students may also attend courses offered by other PhD programs, provided that this is agreed in advance with their (co-)supervisor. The supervisor must confirm that the selected course offers a clear scientific and cultural benefit for the student’s research activities, as these external courses can then be recognized within the individual training plan.
