Zobrazeno 1 - 10
of 833
pro vyhledávání: '"Li Binghui"'
Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks
In this work, we investigate a particular implicit bias in the gradient descent training process, which we term "Feature Averaging", and argue that it is one of the principal factors contributing to non-robustness of deep neural networks. Despite the
Externí odkaz:
http://arxiv.org/abs/2410.10322
Autor:
Li, Binghui, Li, Yuanzhi
Adversarial training is a widely-applied approach to training deep neural networks to be robust against adversarial perturbation. However, although adversarial training has achieved empirical success in practice, it still remains unclear why adversar
Externí odkaz:
http://arxiv.org/abs/2410.08503
Autor:
Li, Binghui, Li, Yuanzhi
Similar to surprising performance in the standard deep learning, deep nets trained by adversarial training also generalize well for $\textit{unseen clean data (natural data)}$. However, despite adversarial training can achieve low robust training err
Externí odkaz:
http://arxiv.org/abs/2306.01271
Autor:
Qiao, Baoshi, Zhang, Zhenzhong, Wang, Yunlong, Huang, Xiaoqian, Zhang, Zhihong, Zheng, Zhiyao, Sun, Xuan, Xie, Xiuhua, Li, Binghui, Chen, Xing, Liu, Kewei, Liu, Lei, Shen, Dezhen
Publikováno v:
In Surfaces and Interfaces 1 January 2025 56
Publikováno v:
In Electric Power Systems Research January 2025 238
Autor:
Li, Yanshuang, Zeng, Huan, Xie, Xiuhua, Li, Binghui, Liu, Jishan, Wang, Shuangpeng, Guo, Dengyang, Li, Yuanzheng, Liu, Weizhen, Shen, Dezhen
Moire materials, created by lattice-mismatch or/and twist-angle, have spurred great interest in excavating novel quantum phases of matter. Latterly, emergent interfacial ferroelectricity has been surprisingly found in spatial inversion symmetry broke
Externí odkaz:
http://arxiv.org/abs/2206.13041
It is well-known that modern neural networks are vulnerable to adversarial examples. To mitigate this problem, a series of robust learning algorithms have been proposed. However, although the robust training error can be near zero via some methods, a
Externí odkaz:
http://arxiv.org/abs/2205.13863
Autor:
Yang, Jialin, Liu, Kewei, zhu, Yongxue, Chen, Xing, Cheng, Zhen, Li, Binghui, Liu, Lei, Shen, Dezhen
Publikováno v:
In Journal of Alloys and Compounds 15 December 2024 1008
Publikováno v:
In Applied Energy 15 December 2024 376 Part B
Publikováno v:
In Materials Today Communications December 2024 41