no code implementations • 2 Jun 2023 • Binghui Li, Yuanzhi Li
We call this phenomenon the $\textit{Clean Generalization and Robust Overfitting (CGRO)}$.
no code implementations • 27 May 2022 • Binghui Li, Jikai Jin, Han Zhong, John E. Hopcroft, LiWei Wang
Moreover, we establish an improved upper bound of $\exp({\mathcal{O}}(k))$ for the network size to achieve low robust generalization error when the data lies on a manifold with intrinsic dimension $k$ ($k \ll d$).
no code implementations • 23 Feb 2022 • Ruichen Li, Binghui Li, Qi Qian, LiWei Wang
Pruning well-trained neural networks is effective to achieve a promising accuracy-efficiency trade-off in computer vision regimes.
2 code implementations • 1 Jul 2021 • Binghui Li, Shiji Xin, Qizhe Zhang
Moreover, we give the theoretical analysis of the ensemble method based on the $1$-Lipschitz property on the certified robustness, which ensures the effectiveness and stability of the algorithm.