Benign overfitting in classification: Provably counter label noise with larger models

K Wen, J Teng, J Zhang - arXiv preprint arXiv:2206.00501, 2022 - arxiv.org
Studies on benign overfitting provide insights for the success of overparameterized deep
learning models. In this work, we examine whether overfitting is truly benign in real-world …