By David Gesbert | July 23, 2019
In the context of PERFUME, a half day workshop was organized on July 5th, 2019, where PERFUME collaborator Vincent Poor gave a seminar entitled “Machine Learning Meets Mobile Communications”
Abstract: Mobile communications and machine learning are two of the most exciting and rapidly developing technological fields of our time. In recent times these two fields have begun to merge in two fundamental ways. First, while mobile communications has developed largely as a model-driven field, the complexities of many emerging communications scenarios is giving rise to the need to introduce data-driven methods into the design and analysis of mobile networks. And, conversely, many machine learning problems are by their nature distributed due to either physical limitations or privacy concerns; this distributed nature gives rise to the need to consider mobile networks as part of learning mechanisms, i.e., as platforms for machine learning. This talk will illuminate these two perspectives, while focusing primarily on the latter, by considering communication issues arising in distributed learning problems such as federated learning and collaborative learning. These issues will be illustrated through examples from recent research in the field.