activity
20052023
most citedGuaranteed Matrix Completion via Non-convex Factorization

339 citations · 2.5k across the 73 of their papers we have counts for

collaborators

74 papers

eess.SP2023★ 1 cited

A Physics-based and Data-driven Approach for Localized Statistical Channel Modeling

Shutao Zhang, Xinzhi Ning, Xi Zheng +3

Localized channel modeling is crucial for offline performance optimization of 5G cellular networks, but the existing channel models are for general scenarios and do not capture loc…

cs.IT2023★ 29 cited

Coordinating Multiple Intelligent Reflecting Surfaces without Channel Information

Fan Xu, Jiawei Yao, Wenhai Lai +4

Conventional beamforming methods for intelligent reflecting surfaces (IRSs) or reconfigurable intelligent surfaces (RISs) typically entail the full channel state information (CSI).…

eess.SP2022★ 1 cited

A Data Quality Assessment Framework for AI-enabled Wireless Communication

Hanning Tang, Liusha Yang, Rui Zhou +5

Using artificial intelligent (AI) to re-design and enhance the current wireless communication system is a promising pathway for the future sixth-generation (6G) wireless network. T…

cs.IT2022★ 35 cited

A Linear Time Algorithm for the Optimal Discrete IRS Beamforming

Shuyi Ren, Kaiming Shen, Xin Li +2

It remains an open problem to find the optimal configuration of phase shifts under the discrete constraint for intelligent reflecting surface (IRS) in polynomial time. The above pr…

cs.LG2022

When Expressivity Meets Trainability: Fewer than Neurons Can Work

Jiawei Zhang, Yushun Zhang, Mingyi Hong +2

Modern neural networks are often quite wide, causing large memory and computation costs. It is thus of great interest to train a narrower network. However, training narrow neural n…

math.OC2022★ 2 cited

On the Iteration Complexity of Smoothed Proximal ALM for Nonconvex Optimization Problem with Convex Constraints

Jiawei Zhang, Wenqiang Pu, Zhi-Quan Luo

It is well-known that the lower bound of iteration complexity for solving nonconvex unconstrained optimization problems is , which can be achieved by standard gradient de…