Generalization Bounds for Adversarial Contrastive Learning

Deep networks are well-known to be fragile to adversarial attacks, and adversarial training is one of the most popular methods used to train a robust model. To take advantage of unlabeled data, recent works have applied adversarial training to contrastive learning (Adversarial Contrastive Learning; ACL for short) and obtain promising robust performance. However, the theory of ACL is not well understood. To fill this gap, we leverage the Rademacher omplexity to analyze the generalization performance of ACL, with a particular …

acl adversarial attacks analyze attacks data focus gap linear networks neural networks performance popular theory training