Title
Distributed Machine Learning Over-the-Air: A Tale of Interference
Abstract
This talk aims to present the current research efforts on the development of implementing machine learning algorithms in wireless systems. Specifically, we provide a comprehensive coverage of a distributed learning paradigm based on over-the-air computing, a.k.a. over-the-air machine learning (OTA-ML). We will present the general architecture, model training algorithm, and an analytical framework that quantifies the convergence rate of OTA-ML. The analysis takes into account key effects from wireless transmissions, namely, channel fading and interference, on the convergence performance and discloses how interference is deteriorating the model training process. Then, we elaborate on several improvements to the OTA-ML from different aspects. Particularly, we discuss the system enhancements from an algorithmic perspective, e.g., adopting the momentum-based approach and/or adaptive optimizations to accelerate the model training. We also introduce model pruning schemes that reduce the computation and communication overheads for OTA-ML. Finally, we will elaborate on the analysis of generalization error of the statistical models trained by OTA-ML, which shows that wireless interference has the positive potential of improving the generalization capability. We will conclude this tutorial by shedding light on future works.
Biographies
Howard H. Yang received the B.E. degree in Communication Engineering from Harbin Institute of Technology (HIT), China, in 2012, and the M.Sc. degree in Electronic Engineering from Hong Kong University of Science and Technology (HKUST), Hong Kong, in 2013. He earned the Ph.D. degree in Electrical Engineering from Singapore University of Technology and Design (SUTD), Singapore, in 2017. He was a Postdoctoral Research Fellow at SUTD from 2017 to 2020, a Visiting Postdoc Researcher at Princeton University from 2018 to 2019, and a Visiting Student at the University of Texas at Austin from 2015 to 2016. Currently, he is an assistant professor with the Zhejiang University/University of Illinois Urbana-Champaign Institute (ZJU-UIUC Institute), Zhejiang University, Haining, China. He is also an adjunct assistant professor with the Department of Electrical and Computer Engineering at the University of Illinois Urbana-Champaign, IL, USA
Dr. Yang’s research interests cover various aspects of wireless communications, networking, and signal processing, currently focusing on the modeling of modern wireless networks, high dimensional statistics, graph signal processing, and machine learning. He serves as an editor for the IEEE Transactions on Wireless Communications, a symposium co-chair for the IEEE International Conference on Communications 2024, and workshop co-chair for IEEE ICASSP, WiOpt, SECON, and SPAWC. Dr. Yang received the IEEE ComSoc Asia-Pacific Outstanding Young Researcher Award in 2023, the IEEE Signal Processing Society Best Paper Award in 2022, and the IEEE WCSP 10-Year Anniversary Excellent Paper Award in 2019. He was recognized as the “6G Rising Star” Young Scholar by the Global 6G Conference in 2024.
