no code implementations • 13 Nov 2023 • Jingtong Su, Ya Shi Zhang, Nikolaos Tsilivis, Julia Kempe
Neural Collapse refers to the curious phenomenon in the end of training of a neural network, where feature vectors and classification weights converge to a very simple geometrical arrangement (a simplex).
no code implementations • 19 Apr 2023 • Jingtong Su, Julia Kempe
2) Replacing the front-end VOneBlock by an off-the-shelf parameter-free Scatternet followed by simple uniform Gaussian noise can achieve much more substantial adversarial robustness without adversarial training.
no code implementations • 18 Dec 2022 • Shiji Xin, Yifei Wang, Jingtong Su, Yisen Wang
Extensive experiments show that our proposed DAT can effectively remove domain-varying features and improve OOD generalization under both correlation shift and diversity shift.
1 code implementation • 24 Jul 2022 • Nikolaos Tsilivis, Jingtong Su, Julia Kempe
In parallel, we revisit prior work that also focused on the problem of data optimization for robust classification \citep{Ily+19}, and show that being robust to adversarial attacks after standard (gradient descent) training on a suitable dataset is more challenging than previously thought.
no code implementations • 29 Sep 2021 • Shiji Xin, Yifei Wang, Jingtong Su, Yisen Wang
Extensive experiments show that our proposed DAT can effectively remove the domain-varying features and improve OOD generalization on both correlation shift and diversity shift tasks.
1 code implementation • NeurIPS 2020 • Jingtong Su, Yihang Chen, Tianle Cai, Tianhao Wu, Ruiqi Gao, Li-Wei Wang, Jason D. Lee
In this paper, we conduct sanity checks for the above beliefs on several recent unstructured pruning methods and surprisingly find that: (1) A set of methods which aims to find good subnetworks of the randomly-initialized network (which we call "initial tickets"), hardly exploits any information from the training data; (2) For the pruned networks obtained by these methods, randomly changing the preserved weights in each layer, while keeping the total number of preserved weights unchanged per layer, does not affect the final performance.