Zobrazeno 11 - 20
of 2 037
pro vyhledávání: '"Zhang, Guojun"'
Discriminatively trained, deterministic neural networks are the de facto choice for classification problems. However, even though they achieve state-of-the-art results on in-domain test sets, they tend to be overconfident on out-of-distribution (OOD)
Externí odkaz:
http://arxiv.org/abs/2311.03683
Out-of-distribution (OOD) generalization is a critical ability for deep learning models in many real-world scenarios including healthcare and autonomous vehicles. Recently, different techniques have been proposed to improve OOD generalization. Among
Externí odkaz:
http://arxiv.org/abs/2308.11778
Layer normalization (LN) is a widely adopted deep learning technique especially in the era of foundation models. Recently, LN has been shown to be surprisingly effective in federated learning (FL) with non-i.i.d. data. However, exactly why and how it
Externí odkaz:
http://arxiv.org/abs/2308.09565
Autor:
Zhang, Xiangkai, Wang, Renxin, Cao, Wenping, Liu, Guochang, Tan, Haoyu, Li, Haoxuan, Wu, Jiaxing, Zhang, Guojun, Zhang, Wendong
Publikováno v:
Sensor Review, 2024, Vol. 44, Issue 3, pp. 395-403.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/SR-01-2024-0032
Autor:
Zeng Zhen, Wang Yi, Wang Huanxiao, Li Yanbing, Chen Benxue, Gou Rongxin, Wang Di, Jiang Yin, Zheng Yuhong, Hamed Khalid E., Fu Li, Zhang Guojun, Wei Zunzheng
Publikováno v:
Nanotechnology Reviews, Vol 13, Iss 1, Pp 1-11 (2024)
Nanomaterials (NMs) have found extensive applications in the realm of ornamental plants due to their unique properties. This article comprehensively discusses four main aspects of NM utilization in ornamental plants: 1) providing new insights into ch
Externí odkaz:
https://doaj.org/article/979dcfbdcc1b4a4bbd256ed69ab5100f
Autor:
Nia, Vahid Partovi, Zhang, Guojun, Kobyzev, Ivan, Metel, Michael R., Li, Xinlin, Sun, Ke, Hemati, Sobhan, Asgharian, Masoud, Kong, Linglong, Liu, Wulong, Chen, Boxing
Deep models are dominating the artificial intelligence (AI) industry since the ImageNet challenge in 2012. The size of deep models is increasing ever since, which brings new challenges to this field with applications in cell phones, personal computer
Externí odkaz:
http://arxiv.org/abs/2303.15464
We show that the canonical approach for training differentially private GANs -- updating the discriminator with differentially private stochastic gradient descent (DPSGD) -- can yield significantly improved results after modifications to training. Sp
Externí odkaz:
http://arxiv.org/abs/2302.02936
Autor:
Imani, Ehsan, Zhang, Guojun, Li, Runjia, Luo, Jun, Poupart, Pascal, Torr, Philip H. S., Pan, Yangchen
Recent work has highlighted the label alignment property (LAP) in supervised learning, where the vector of all labels in the dataset is mostly in the span of the top few singular vectors of the data matrix. Drawing inspiration from this observation,
Externí odkaz:
http://arxiv.org/abs/2211.14960
In this paper, we propose and analyze an efficient Halpern-Peaceman-Rachford (HPR) algorithm for solving the Wasserstein barycenter problem (WBP) with fixed supports. While the Peaceman-Rachford (PR) splitting method itself may not be convergent for
Externí odkaz:
http://arxiv.org/abs/2211.14881
Modern machine learning systems achieve great success when trained on large datasets. However, these datasets usually contain sensitive information (e.g. medical records, face images), leading to serious privacy concerns. Differentially private gener
Externí odkaz:
http://arxiv.org/abs/2208.03409