Learn to Optimize for Wireless Communications
by: Prof. Wei Yu, University of Toronto
Abstract: Machine learning will have an important role to play in the optimization of future-generation physical-layer wireless communication system design for the following two reasons. First, traditional wireless communication design always relies on the channel model, but models are inherently only an approximation to the reality. In wireless environments where the models are complex and the channels are costly to estimate, a machine learning based approach that performs system-level optimization without explicit channel estimation can significantly outperform the traditional channel estimation based approaches. Second, modern wireless communication design often involves optimization problems that are high-dimensional, nonconvex, and difficult to solve efficiently. By exploring the availability of training data, a neural network may be able to learn the solution of an optimization problem directly. This can lead to a more efficient way to solve nonconvex optimization problems. In this talk, I will use examples from optimizing a reconfigurable intelligent surface (RIS) system, precoding for a massive multiple-input multiple-output (MIMO) system, and active sensing for mmWave channel initial alignment to illustrate the benefit of learning-based physical-layer communication system design. We show that matching the neural network architecture to the problem structure is crucial for the success of learning based approaches.
Biography: Wei Yu received the B.A.Sc. degree in Computer Engineering and Mathematics from the University of Waterloo, and M.S. and Ph.D. degrees in Electrical Engineering from Stanford University. He has been with the Electrical and Computer Engineering Department at the University of Toronto since 2002, where he is now Professor and holds a Canada Research Chair (Tier 1) in Information Theory and Wireless Communications. Prof. Wei Yu is a Fellow of IEEE, a Fellow of the Canadian Academy of Engineering, and a member of the College of New Scholars, Artists and Scientists of the Royal Society of Canada. He received the Steacie Memorial Fellowship in 2015, the IEEE Marconi Prize Paper Award in Wireless Communications in 2019, the IEEE Communications Society Award for Advances in Communication in 2019, the IEEE Signal Processing Society Best Paper Award in 2008, 2017 and 2021, the Journal of Communications and Networks Best Paper Award in 2017, and the IEEE Communications Society Best Tutorial Paper Award in 2015. Prof. Wei Yu was an IEEE Communications Society Distinguished Lecturer in 2015-16. He served as the Chair of the Signal Processing for Communications and Networking Technical Committee of the IEEE Signal Processing Society in 2017-18. Prof. Wei Yu was the President of the IEEE Information Theory Society in 2021.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
- University of Victoria
- Victoria, British Columbia
- Canada
- Building: ECS
- Room Number: 660
- Contact Event Hosts
- Co-sponsored by Xiaodai Dong
Speakers
Learn to Optimize for Wireless Communications
Abstract: Machine learning will have an important role to play in the optimization of future-generation physical-layer wireless communication system design for the following two reasons. First, traditional wireless communication design always relies on the channel model, but models are inherently only an approximation to the reality. In wireless environments where the models are complex and the channels are costly to estimate, a machine learning based approach that performs system-level optimization without explicit channel estimation can significantly outperform the traditional channel estimation based approaches. Second, modern wireless communication design often involves optimization problems that are high-dimensional, nonconvex, and difficult to solve efficiently. By exploring the availability of training data, a neural network may be able to learn the solution of an optimization problem directly. This can lead to a more efficient way to solve nonconvex optimization problems. In this talk, I will use examples from optimizing a reconfigurable intelligent surface (RIS) system, precoding for a massive multiple-input multiple-output (MIMO) system, and active sensing for mmWave channel initial alignment to illustrate the benefit of learning-based physical-layer communication system design. We show that matching the neural network architecture to the problem structure is crucial for the success of learning based approaches.
Biography:
Biography: Wei Yu received the B.A.Sc. degree in Computer Engineering and Mathematics from the University of Waterloo, and M.S. and Ph.D. degrees in Electrical Engineering from Stanford University. He has been with the Electrical and Computer Engineering Department at the University of Toronto since 2002, where he is now Professor and holds a Canada Research Chair (Tier 1) in Information Theory and Wireless Communications. Prof. Wei Yu is a Fellow of IEEE, a Fellow of the Canadian Academy of Engineering, and a member of the College of New Scholars, Artists and Scientists of the Royal Society of Canada. He received the Steacie Memorial Fellowship in 2015, the IEEE Marconi Prize Paper Award in Wireless Communications in 2019, the IEEE Communications Society Award for Advances in Communication in 2019, the IEEE Signal Processing Society Best Paper Award in 2008, 2017 and 2021, the Journal of Communications and Networks Best Paper Award in 2017, and the IEEE Communications Society Best Tutorial Paper Award in 2015. Prof. Wei Yu was an IEEE Communications Society Distinguished Lecturer in 2015-16. He served as the Chair of the Signal Processing for Communications and Networking Technical Committee of the IEEE Signal Processing Society in 2017-18. Prof. Wei Yu was the President of the IEEE Information Theory Society in 2021.