Cross-entropy is a widely used loss function in applications. It coincides with the logistic loss
applied to the outputs of a neural network, when the softmax is used. But, what guarantees …

In this work, we aim to characterize the statistical complexity of realizable regression both in
the PAC learning setting and the online learning setting. Previous work had established the …

We consider a model of robust learning in an adversarial environment. The learner gets
uncorrupted training data with access to possible corruptions that may be effected by the …

In this work, we investigate the interplay between memorization and learning in the context
of\emph {stochastic convex optimization}(SCO). We define memorization via the information …

We initiate the study of computability requirements for adversarially robust learning.
Adversarially robust PAC-type learnability is by now an established field of research …

We obtain the first positive results for bounded sample compression in the agnostic
regression setting with the $\ell_p $ loss, where $ p\in [1,\infty] $. We construct a generic …

We study robustness to test-time adversarial attacks in the regression setting with $\ell_p $
losses and arbitrary perturbation sets. We address the question of which function classes …

In adversarial machine learning, neural networks suffer from a significant issue known as
robust overfitting, where the robust test accuracy decreases over epochs (Rice et al., 2020) …

In many real-world settings exact perturbation sets to be used by an adversary are not
plausibly available to a learner. While prior literature has studied both scenarios with …

We consider a model of robust learning in an adversarial environment. The learner gets
uncorrupted training data with access to possible corruptions that may be affected by the …