Search Results for author:
Found 4 papers, 1 papers with code
Towards Understanding Clean Generalization and Robust Overfitting in Adversarial Training
We call this phenomenon the $\textit{Clean Generalization and Robust Overfitting (CGRO)}$.
Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power
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 $k$ ($k \ll d$).
Reconstruction Task Finds Universal Winning Tickets
Pruning well-trained neural networks is effective to achieve a promising accuracy-efficiency trade-off in computer vision regimes.
Boosting Certified $\ell_\infty$ Robustness with EMA Method and Ensemble Model
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.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
