Benign Overfitting in Adversarially Robust Linear Classification
원문 초록
"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, a series of works have provided theoretical justification in over-parameterized linear regression, classification, and kernel methods. However, it is not clear if benign overfitting still occurs in the presence of adversarial examples, i.e., examples with tiny and intentional perturbations to fool the classifiers. In this paper, we show that benign overfitting indeed occurs in adversarial training, a principled approach to defend against adversarial examples. In detail, we prove the risk bounds of the adversarially trained linear classifier on the mixture of sub-Gaussian data under $\ell_p$ adversarial perturbations. Our result suggests that under moderate perturbations, adversarially trained linear classifiers can achieve the near-optimal standard and adversarial risks, despite overfitting the noisy training data. Numerical experiments validate our theoretical findings.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation
AI-Enhanced Pediatric Pneumonia Detection: A CNN-Based Approach Using Data Augmentation and Generative Adversarial Networks (GANs)
Hybrid-View Attention for csPCa Classification in TRUS
One Prototype Is Enough: Single-Prototype Activation for Interpretable Image Classification
Brain-inspired interpretable reservoir computing with resonant recurrent neural networks
Malware Classification Leveraging NLP & Machine Learning for Enhanced Accuracy
토론
이 논문과 연결된 포럼 글이 아직 없습니다.