Traditionally, communication system research was based on system modelling and abstraction followed by performance evaluation using Monte Carlo simulations or system design using optimization. However, with the renaissance of ML techniques, various learning-assisted method have been adopted to
1) replace conventional model-based estimation and
2) approximate/accelerate complicated optimization problems.
In this talk, we will review the fundamentals of this paradigm shift and study some representative examples from the domains of dynamic spectrum management, resource allocation and content delivery systems. The presented concepts and results draw from the Advanced ERC Grant AGNOSTIC.
Symeon Chatzinotas is currently Assistant Professor and Deputy Head of the SIGCOM Research Group at SnT University of Luxembourg. He is leading the SnT’s activities on communications and networking along with a team of 45 researchers. In the past, he has been a Visiting Professor at the University of Parma, Italy and he was involved in numerous Research and Development projects for the National Center for Scientific Research Demokritos, the Center of Research and Technology Hellas and the Center of Communication Systems Research, University of Surrey.
He received the M.Eng. degree in telecommunications from the Aristotle University of Thessaloniki, Thessaloniki, Greece, in 2003, and the M.Sc. and Ph.D. degrees in electronic engineering from the University of Surrey, Surrey, U.K., in 2006 and 2009, respectively.
He has authored more than 350 technical papers cited 4000 times with an H-index of 31 according to GS. He was a co-recipient of the 2014 IEEE Distinguished Contributions to Satellite Communications Award, the 2015 CROWNCOM Best Paper Award and the 2018 EURASIC JWCN Best Paper Award.
Symeon Chatzinotas’s website http://sites.google.com/view/symeonchatzinotas