Efficient Federated Learning over Networks
IEEE ComSoc Italy Chapter Distinguished Lecture Tour
Speaker: Prof. Carlo Fischione (KTH, IEEE ComSoc Distinguished Lecturer)
Title of Talk: Efficient Federated Learning over Networks
Abstract: Federated learning is a distributed stochastic optimization problem in which multiple agents collaboratively minimize a global objective through local computations and iterative information exchange. While classical distributed optimization theory often assumes reliable and ideal communication links, wireless systems introduce severe constraints in terms of bandwidth, latency, interference, fading, and energy consumption. As a result, communication becomes a fundamental bottleneck for scalability and convergence. This seminar presents recent advances on communication computation efficient federated learning over networks, with emphasis on the interplay between optimization theory, information transmission, and function computation. The talk discusses distributed stochastic optimization methods under communication constraints, including compressed gradient methods, local-update schemes, adaptive aggregation, and convergence analysis under imperfect information exchange. Finally, the seminar discusses emerging theoretical directions toward Networked AI, including learning under communication uncertainty, non-coherent distributed computation, reliability-aware learning, and the joint design of communication, computation, and inference in large-scale distributed AI systems.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
- Gran Sassos Science Institute
- L'Aquila, Abruzzi
- Italy
- Contact Event Host
- Co-sponsored by Gran Sasso Science Institute
Speakers
Carlo Fischione of KTH
Biography:
Dr. Carlo Fischione is full Professor at KTH Royal Institute of Technology, Electrical Engineering and Computer Science, Division of Network and Systems Engineering (NSE), Stockholm, Sweden. Prof. Fischione is Fellow of IEEE (the Institute of Electrical and Electronic Engineers), AAIS (Academy of Artificial Intelligence Sciences), DF (KTH Digital Futures research center), and DASP (the Italian academy of history Deputazione Abruzzese di Storia Patria) and is Distinguished Lecturer of the IEEE Communication Society. He is Director of the undergraduate education at NSE Department of KTH, Chair of the IEEE Machine Learning for Communications Emerging Technologies Initiative, founding General Chair and Steering Commitee Chair of the IEEE International Conference on Machine Learning for Communications and Networking – IEEE ICMLCN, and was the founding Director of the KTH-Ericsson Data Science Micro Degree Program directed to Ericsson globally. Prof. Fischione is the IEEE ComSoc delegate to the IEEE AI Alliance. He received the Ph.D. degree in Electrical and Information Engineering (3/3 years) in May 2005 and the Laurea degree in Electronic Engineering (Laurea, Summa cum Laude, 5/5 years) in April 2001, both from University of L’Aquila, Italy. He received the Starting Grant of the Swedish Research Council in 2008. Prof. Fischione has held research positions at Massachusetts Institute of Technology, Cambridge, MA (2015, Visiting Professor); Harvard University, Cambridge, MA (2015, Associate); and University of California at Berkeley, CA (2004-2005, Visiting Scholar, and 2007-2008, Research Associate). He is Professor on the Doctoral School of University of L’Aquila, Italy, Department of Mathematics, Information Engineering, and Computer Science. His research interests include applied optimization, wireless Internet of Things, and machine learning. He received a number of awards, such as the “IEEE Communication Society S. O. Rice” award for the best IEEE Transactions on Communications paper of 2018, the best paper award of IEEE Transactions on Industrial Informatics (2007). He is Editor of IEEE Transactions on Communications (Machine Learning for Communications area) and IEEE Transactions on Machine Learning for Communication and Networking, and has served as Associated Editor of IFAC Automatica (2014-2019). He is co-founder of the company ELK.Audio.
Email:
Address:Sweden
This event is an officially approved IEEE ComSoc Distinguished Lecturer Tour talk