Interpolation can hurt robust generalization even when there is no noise

Interpolation can hurt robust generalization even when there is no noise

5 August 2021

Konstantin Donhauser

Alexandru cTifrea

Reinhard Heckel

Papers citing "Interpolation can hurt robust generalization even when there is no noise"

12 / 12 papers shown

Title
Towards unlocking the mystery of adversarial fragility of neural networks Jingchao Gao Raghu Mudumbai Xiaodong Wu Jirong Yi Catherine Xu Hui Xie Weiyu Xu 26 1 0 23 Jun 2024
The Surprising Harmfulness of Benign Overfitting for Adversarial Robustness Yifan Hao Tong Zhang AAML 19 4 0 19 Jan 2024
Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach Shaopeng Fu Di Wang AAML 28 1 0 09 Oct 2023
On Achieving Optimal Adversarial Test Error Justin D. Li Matus Telgarsky AAML 17 1 0 13 Jun 2023
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels Simone Bombari Shayan Kiyani Marco Mondelli AAML 16 10 0 03 Feb 2023
Strong inductive biases provably prevent harmless interpolation Michael Aerni Marco Milanta Konstantin Donhauser Fanny Yang 30 9 0 18 Jan 2023
Margin-based sampling in high dimensions: When being active is less efficient than staying passive A. Tifrea Jacob Clarysse Fanny Yang 17 2 0 01 Dec 2022
Rethinking Cost-sensitive Classification in Deep Learning via Adversarial Data Augmentation Qiyuan Chen Raed Al Kontar Maher Nouiehed Xi Yang Corey A. Lester AAML 13 2 0 24 Aug 2022
Why adversarial training can hurt robust accuracy Jacob Clarysse Julia Hörrmann Fanny Yang AAML 11 18 0 03 Mar 2022
Interpolation and Regularization for Causal Learning L. C. Vankadara Luca Rendsburg U. V. Luxburg D. Ghoshdastidar CML 21 1 0 18 Feb 2022
Hierarchical Shrinkage: improving the accuracy and interpretability of tree-based methods Abhineet Agarwal Yan Shuo Tan Omer Ronen Chandan Singh Bin-Xia Yu 63 27 0 02 Feb 2022
NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labels Jingfeng Zhang Xilie Xu Bo Han Tongliang Liu Gang Niu Li-zhen Cui Masashi Sugiyama NoLa AAML 10 9 0 31 May 2021