The curse of overparametrization in adversarial training: Precise analysis of robust
generalization for random features regressi Page 1 The Annals of Statistics 2024, Vol. 52, No. 2 …

Benign overfitting is the phenomenon wherein none of the predictors in the hypothesis class
can achieve perfect accuracy (ie, non-realizable or noisy setting), but a model that …

Abstract Machine learning models are vulnerable to adversarial perturbations, and a thought-
provoking paper by Bubeck and Sellke has analyzed this phenomenon through the lens of …

Machine learning classifiers with high test accuracy often perform poorly under adversarial
attacks. It is commonly believed that adversarial training alleviates this issue. In this paper …

Recent empirical and theoretical studies have established the generalization capabilities of
large machine learning models that are trained to (approximately or exactly) fit noisy data. In …

In this paper, we study the adversarial robustness of deep neural networks for classification
tasks. We look at the smallest magnitude of possible additive perturbations that can change …

It is widely believed that given the same labeling budget, active learning (AL) algorithms like
margin-based active learning achieve better predictive performance than passive learning …

Cost-sensitive classification is critical in applications where misclassification errors widely
vary in cost. However, overparameterization poses fundamental challenges to the cost …

Recent work shows that in complex model classes, interpolators can achieve statistical
generalization and even be optimal for statistical learning. However, despite increasing …

While large datasets facilitate the learning of a robust representation of the data manifold,
the ability to obtain similar performance over small datasets is clearly computationally …