Keywords: machine learning, neural networks, optimization, suboptimal solutions, mathematical games.Abstract. Since the very beginning, there has been a fruitful exchange between machine learning and optimization. While machine learning exploits optimization models and algorithms, it simultaneously poses problems which often constitute optimization challenges. This cross- fertilization is particularly evident nowadays. Many applications produce data that have to be processed and many other applications are based on data that have already been processed. In society, data-producers and data-consumers continuously exchange their roles. At the same time, scientists generate and collect huge amounts of data and need to develop methodologies for data analysis. This requires the use of ever more powerful approaches and techniques. Among these improvements, those coming from the field of optimization and game theory surely play a basic role. In this talk, I provide a non-technical review of some optimization paradigms and machine- learning techniques used in my research and I emphasize some aspects at the confluence of these two disciplines. Then, I focus on some optimization problems that exploit machine learning and game-theoretical optimization models. The interplay between machine learning and optimization continues to develop, and its benefits are there for all to see.Short bio. Marcello Sanguineti is Full Professor of Operations Research at the University of Genova. He is also Guest Scholar at the AXES (Analysis of compleX Economic Systems) Research Unit of IMT-School of Advanced Studies (Lucca, Italy) and Research Associate at the Institute for Marine Engineering of the National Research Council of Italy. He co- authored over 200 research papers in archival journals, book chapters, and international conference proceedings, and the book “Neural Approximations for Optimal Control and Decision” (Springer, Communications and Control Engineering Series, 2020). His main research interests are infinite-dimensional programming, machine learning, complex networks analysis, mathematics of neurocomputing, network and team optimization, optimal control, and affective computing. Prof. Sanguineti was a member of the Program Committees of several conferences, Chair of the Organizing Committee of the Int. Conf. ICNPAA 2008, and member of the Organizing Committee of the Int. Conf. on Optimization and Decision Science, 2019. He coordinated several national and international research projects on approximate solution of optimization problems and mathematics of neurocomputing. He is Area Editor of the journal Soft Computing and member of the Editorial Boards of the IEEE Transactions on Neural Networks and Learning Systems, Neural Networks, Neurocomputing, and Neural Processing Letters.

https://indico.math.cnrs.fr/event/9970/