Zepeng Zhang
Zepeng Zhang now is a Ph.D. student at École Polytechnique Fédérale de Lausanne (EPFL), Switzerland. Previously, he received his master degree (with honors) from ShanghaiTech University and bachelor degree (with honors) from Wuhan University. He also had the opportunity to visit Peking University and City University of Hong Kong as a research intern.
To get more recent info about him, please visit zepengzhang.com.
At the DSAI lab, Zepeng has primarily focused his research on two key areas: graph signal processing (an optimization perspective to comprehend and design graph neural networks) and communication signal processing (nonconvex optimization for rate maximization problems).
optimization induced graph neural networks
-
Towards Understanding Graph Neural Networks: An Algorithm Unrolling Perspective
Zepeng Zhang and Ziping Zhao.- Short version: Designing Graph Neural Networks via Algorithm Unrolling
Zepeng Zhang and Ziping Zhao, International Workshop on Deep Learning on Graphs: Methods and Applications (DLG), 2022.
- Short version: Designing Graph Neural Networks via Algorithm Unrolling
-
ASGNN: Graph Neural Networks with Adaptive Structure
Zepeng Zhang, Ziping Zhao, Songtao Lu, and Zengfeng Huang.- Short version: Graph Neural Networks With Adaptive Structure
Zepeng Zhang, Ziping Zhao, Songtao Lu, and Zengfeng Huang, Graph Signal Processing Workshop (GSP), 2024.
- Short version: Graph Neural Networks With Adaptive Structure
optimization for weighted sum-rate maximization problems
-
Discerning and Enhancing the Weighted Sum-Rate Maximization Algorithms in Communications
Zepeng Zhang, Ziping Zhao, Kaiming Shen, Daniel P. Palomar, and Wei Yu.- Short version: Enhancing the Efficiency of WMMSE and FP for Beamforming by Minorization-Maximization
Zepeng Zhang, Ziping Zhao, and Kaiming Shen, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023.
- Short version: Enhancing the Efficiency of WMMSE and FP for Beamforming by Minorization-Maximization
-
Rate Maximizations for Reconfigurable Intelligent Surface-Aided Wireless Networks: A Unified Framework via Block Minorization-Maximization
Zepeng Zhang and Ziping Zhao.- Short version: Weighted Sum-Rate Maximization for Multi-Hop RIS-Aided Multi-User Communications: A Minorization-Maximization Approach
Zepeng Zhang and Ziping Zhao, IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 2021 (Best Student Paper Award Finalist).
- Short version: Weighted Sum-Rate Maximization for Multi-Hop RIS-Aided Multi-User Communications: A Minorization-Maximization Approach
-
On Convergence Rates of Quadratic Transform and WMMSE Methods
Kaiming Shen, Ziping Zhao, Yannan Chen, Zepeng Zhang, and Hei Victor Cheng.- Short version: Accelerating Quadratic Transform and WMMSE
Kaiming Shen, Ziping Zhao, Yannan Chen, Zepeng Zhang, and Hei Victor Cheng, IEEE International Symposium on Information Theory (ISIT), 2024.
- Short version: Accelerating Quadratic Transform and WMMSE
others
-
Vast Portfolio Selection With Submodular Norm Regularizations
Zepeng Zhang and Ziping Zhao, European Signal Processing Conference (EUSIPCO), 2021. -
Scalable Financial Index Tracking with Graph Neural Networks
Zepeng Zhang and Ziping Zhao, IEEE Statistical Signal Processing Workshop (SSP), 2021. -
A Deep Learning-Aided Approach to Portfolio Design for Financial Index Tracking
Zepeng Zhang and Ziping Zhao, Annual Asilomar Conference on Signals, Systems, and Computers (Asilomar), 2020. -
Multi-Period Portfolio Optimization for Index Tracking in Finance
Xiuyuan Huang, Zepeng Zhang, and Ziping Zhao, Annual Asilomar Conference on Signals, Systems, and Computers (Asilomar), 2020.