paper-with-me

Papers

Understanding Overfitting in Adversarial Training via Kernel Regression

2023-04-13 · Teng Zhang, Kang Li

Adversarial training and data augmentation with noise are widely adopted techniques to enhance the performance of neural networks. This paper investigates adversarial training and data augmentation with noise in the context of regularized regression in a reproducing kernel Hilbert space (RKHS). We establish the limiting formula for these techniques as the attack and noise size, as well as the regularization parameter, tend to zero. Based on this limiting formula, we analyze specific scenarios and demonstrate that, without appropriate regularization, these two methods may have larger generalization error and Lipschitz constant than standard kernel regression. However, by selecting the appropriate regularization parameter, these two methods can outperform standard kernel regression and achieve smaller generalization error and Lipschitz constant. These findings support the empirical observations that adversarial training can lead to overfitting, and appropriate regularization methods, such as early stopping, can alleviate this issue.

📄 PDF Abstract BibTeX arXiv:2304.06326

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentationregression

Similar Papers 제목 키워드 기반

Benign Overfitting in Adversarially Robust Linear Classification

2021-12-31 · Jinghui Chen, Yuan Cao, Quanquan Gu

"Benign overfitting", where classifiers memorize noisy training data yet still achieve a good generalization performance, has drawn great attention in the machine learning community. To explain this surprising phenomenon…

Classification

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting

2022-07-14 · Neil Mallinar, James B. Simon, Amirhesam Abedsoltan, Parthe Pandit 외

The practical success of overparameterized neural networks has motivated the recent scientific study of interpolating methods, which perfectly fit their training data. Certain interpolating methods, including neural netw…

Learning Theory

Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension

2023-05-23 · NeurIPS 2023 11 · Moritz Haas, David Holzmüller, Ulrike Von Luxburg, Ingo Steinwart

The success of over-parameterized neural networks trained to near-zero training error has caused great interest in the phenomenon of benign overfitting, where estimators are statistically consistent even though they inte…

regression

Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality

2024-09-05 · Marko Medvedev, Gal Vardi, Nathan Srebro

We consider the overfitting behavior of minimum norm interpolating solutions of Gaussian kernel ridge regression (i.e. kernel ridgeless regression), when the bandwidth or input dimension varies with the sample size. For …

regression

Can overfitted deep neural networks in adversarial training generalize? -- An approximation viewpoint

2024-01-24 · Zhongjie Shi, Fanghui Liu, Yuan Cao, Johan A. K. Suykens

Adversarial training is a widely used method to improve the robustness of deep neural networks (DNNs) over adversarial perturbations. However, it is empirically observed that adversarial training on over-parameterized ne…