Zobrazeno 1 - 10
of 84
pro vyhledávání: '"Zhang, Naifu"'
One of the main focuses in distributed learning is communication efficiency, since model aggregation at each round of training can consist of millions to billions of parameters. Several model compression methods, such as gradient quantization and spa
Externí odkaz:
http://arxiv.org/abs/2206.13984
One of the main focus in federated learning (FL) is the communication efficiency since a large number of participating edge devices send their updates to the edge server at each round of the model training. Existing works reconstruct each model updat
Externí odkaz:
http://arxiv.org/abs/2101.08696
Autor:
Capel, Nicholas, Zhang, Naifu
There have been attempts in reinforcement learning to exploit a priori knowledge about the structure of the system. This paper proposes a hybrid reinforcement learning controller which dynamically interpolates a model-based linear controller and an a
Externí odkaz:
http://arxiv.org/abs/2009.05866
Publikováno v:
Robotics: Science and System (RSS2021)
In this paper, we propose a novel task, Manipulation Question Answering (MQA), where the robot performs manipulation actions to change the environment in order to answer a given question. To solve this problem, a framework consisting of a QA module a
Externí odkaz:
http://arxiv.org/abs/2003.04641
Autor:
Zhang, Naifu, Tao, Meixia
Federated learning (FL) is a promising technique that enables many edge devices to train a machine learning model collaboratively in wireless networks. By exploiting the superposition nature of wireless waveforms, over-the-air computation (AirComp) c
Externí odkaz:
http://arxiv.org/abs/2003.02089
Autor:
Zhou, Yu, Zhang, Hong, Zhang, Simeng, Zhang, Jiayue, Di, Hong, Zhang, Lin, Dong, Ling, Lu, Qing, Zeng, Xing, Liu, Xianjun, Zhang, Naifu, Wang, Zhenhua
Publikováno v:
In International Journal of Biological Macromolecules 31 December 2023 253 Part 3
Publikováno v:
In Chaos, Solitons and Fractals: the interdisciplinary journal of Nonlinear Science, and Nonequilibrium and Complex Phenomena May 2023 170
Proactive caching is an effective way to alleviate peak-hour traffic congestion by prefetching popular contents at the wireless network edge. To maximize the caching efficiency requires the knowledge of content popularity profile, which however is of
Externí odkaz:
http://arxiv.org/abs/1803.04675
Publikováno v:
In Journal of Crystal Growth 15 December 2022 600
Autor:
Xiong, Huifan, Mao, Weiwei, Wang, Rong, Liu, Shuai, Zhang, Naifu, Song, Lihui, Yang, Deren, Pi, Xiaodong
Publikováno v:
In Materials Today Physics December 2022 29