1 citations · 1 across the 8 of their papers we have counts for
8 papers
Beyond the Matrix Sign: Quadratic Spectral Descent
Qiaozhe Zhang, Jun Sun, Yingzhuang Liu
Muon emerges as a strong competitor of the AdamW for LLM pretraining, because the matrix-wise update it employs can potentially incur smaller second-order penalty than the once dom…
Over-the-Air Interference Nulling Using Passive RIS for Two-Way K-User Interference Channel
Junzhi Wang, Jun Sun, Limin Liao +2
Interference constitutes the fundamental performance bottleneck in wireless networks. Meanwhile, reconfigurable intelligent surface (RIS) has emerged as a promising technique for i…
Over-the-Air Interference Nulling Using Active RIS
Junzhi Wang, Jun Sun, Limin Liao +2
Interference fundamentally limits the performance of dense wireless networks, and reconfigurable intelligent surfaces (RIS) have recently emerged as a promising means of enabling i…
Digital Self-Interference Cancellation in Full-Duplex Radios: A Fundamental Limit Perspective
Limin Liao, Jun Sun, Junzhi Wang +4
D-SIC is of crucial importance for the implementation of IBFD radios. Unfortunately, the achievable performance limit remains underexplored. To fill this gap, in this paper we aim…
Rényi Sharpness: A Novel Sharpness that Strongly Correlates with Generalization
Qiaozhe Zhang, Jun Sun, Ruijie Zhang +1
Sharpness (of the loss minima) is widely believed to be a good indicator of generalization of neural networks. Unfortunately, the correlation between existing sharpness measures an…
Analog Self-Interference Cancellation in Full-Duplex Radios: A Fundamental Limit Perspective
Limin Liao, Jun Sun, Junzhi Wang +1
Analog self-interference cancellation (A-SIC) plays a crucial role in the implementation of in-band full-duplex (IBFD) radios, due to the fact that the inherent transmit (Tx) noise…
Achieving Interference-Free Degrees of Freedom in Cellular Networks via RIS
Junzhi Wang, Jun Sun, Zheng Xiao +2
It's widely perceived that Reconfigurable Intelligent Surfaces (RIS) cannot increase Degrees of Freedom (DoF) due to their relay nature. A notable exception is Jiang \& Yu's work.…
How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective
Qiaozhe Zhang, Ruijie Zhang, Jun Sun +1
Network pruning is a commonly used measure to alleviate the storage and computational burden of deep neural networks. However, the fundamental limit of network pruning is still lac…