Distributed Machine Learning over Wireless Channels


Speaker:      Prof. Deniz GunduzImperial College London
Time:           18:00-19:00  Nov.19.2021 

Host:            Prof. Yuanming Shi

Link:                ZOOM:     https://us06web.zoom.us/j/89614730730?pwd=WVk1T0grbHJSWGdLSmRVU3Bma09qUT09  会议号:986 4342 5115  密码:536655


                       Bilibili:        https://live.bilibili.com/22272691

Abstract:    Edge devices collect massive amounts of data, opening up new potentials for machine learning applications. Machine learning at the edge can benefit from exploiting both the data and the processing power distributed across many wireless devices, but this brings about many new challenges including the low latency requirements of learning applications, privacy concerns preventing data sharing, and the impact of noise and interference on the convergence of the learning process. Overcoming these challenges while meeting the accuracy requirements of machine learning tasks calls for a new paradigm of semantic-oriented communication network design. In this talk, I will present our recent results on efficient distributed inference and training over wireless networks taking into account channel impairments and resource limitations of wireless devices, as well as the semantics of the underlying learning tasks. This will involve bringing together novel communication and coding techniques with distributed learning and inference algorithms.

Bio:    Deniz Gündüz received the M.S. and Ph.D. degrees in electrical engineering from NYU Polytechnic School of Engineering (formerly Polytechnic University), Brooklyn, NY, in 2004 and 2007, respectively. He is currently a Professor in Information Processing in the Electrical and Electronic Engineering Department of Imperial College London, UK, where he leads the Information Processing and Communications Laboratory (IPC-Lab), and serves as the Deputy Head of the Intelligent Systems and Networks Group. He is also a part-time faculty member at the University of Modena and Reggio Emilia, Italy. Previously, he has held positions at Princeton University, Stanford University, CTTC and University of Padova. His research interests lie in the areas of communications and information theory, machine learning, security and privacy. Prof. Gündüz is an Area Editor for the  IEEE Transactions on Information Theory, the IEEE Transactions on Communications and the IEEE Journal on Selected Areas in Communications (JSAC) - Special Series on Machine Learning in Communications and Networks. He also serves as an Editor of the IEEE Transactions on Wireless Communications. He is a Distinguished Lecturer for the IEEE Information Theory Society (2020-22).