← Search

Erin George

2 accepted papers

2024

Benign overfitting in leaky ReLU networks with moderate input dimension

NeurIPS 2024spotlight

The problem of benign overfitting asks whether it is possible for a model to perfectly fit noisy training data and still generalize well. We study benign overfitting in two-layer leaky ReLU networks trained with the hinge loss on a binary classification task. We consider input data which can be deco…

Cited by 4SourcePDFScholar
2023

Training shallow ReLU networks on noisy data using hinge loss: when do we overfit and is it benign?

NeurIPS 2023spotlight

We study benign overfitting in two-layer ReLU networks trained using gradient descent and hinge loss on noisy data for binary classification. In particular, we consider linearly separable data for which a relatively small proportion of labels are corrupted or flipped. We identify conditions on the m…

Cited by 9SourcePDFScholar