报告题目：同步分布式学习的资源分配和通信调度及一些凸优化证明

报告时间：12月18日（周四）14:30

报告地点：武汉大学电子信息学院于刚·宋晓楼B603会议室

报  告  人：Paul Zheng，助理研究员，德国亚琛工业大学

邀  请  人：朱尧  研究员

Abstract: 

Distributed edge learning (DL) is considered a cornerstone of intelligence enablers, since it allows for collaborative training without the necessity for local clients to share raw data with other parties, thereby preserving privacy and security.

Integrating DL into the 6G networks requires a coexistence design with existing services such as high-bandwidth (HB) traffic like eMBB. Current designs in the literature mainly focus on communication round-wise designs that assume a rigid resource allocation throughout each communication round (CR). However, rigid resource allocation within a CR is a highly inefficient and inaccurate representation of the system’s realistic behavior. This is due to the heterogeneous nature of the system, as clients inherently may need to access the network at different times.

This work zooms into one arbitrary CR, and demonstrates the importance of considering a time-dependent resource sharing design with HB traffic. We first formulate a time-step-wise optimization problem to minimize the consumed time by DL within the CR while constrained by a DL energy budget. Due to its intractability, a session-based optimization problem is formulated assuming a CR lasts less than a large-scale coherence time. Some scheduling properties of such multi-server joint communication scheduling and resource allocation framework have been established. Some interesting proves involving convex optimization will also be presented.

Bio:

Paul Zheng received the M.Sc. degree in information technology and computer engineering from RWTH Aachen University, Aachen, Germany, and the Engineering degree (Dipl. Ing./M. Eng.) from Ecole Centrale de Lyon (France) in 2020. He also holds a B.Sc. degree in General Mathematics from Université Claude Bernard Lyon 1 (France). From June to December 2020, he was with Univ. Paris-Saclay, CentraleSupelec, CVN, Inria-Opis, France. Since 2021, he has been working toward a Ph.D. degree with the Chair of Information Theory and Data Analytics at RWTH Aachen University. His research interests include optimization for federated learning design in wireless networks, signal processing and ultra-reliable and low-latency communication.

欢迎感兴趣的老师和同学们积极参与！