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 study fast rates of convergence in the setting of nonparametric online regression, namely
where regret is defined with respect to an arbitrary function class which has bounded …

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 this work we initiate the study of regression in the universal rates framework of Bousquet
et al. Unlike the traditional uniform learning setting, we are interested in obtaining learning …

In statistical learning theory, determining the sample complexity of realizable binary
classification for VC classes was a long-standing open problem. The results of Simon [1] and …

Abstract Machine learning is a rapidly growing field of computer science that has the
potential to revolutionize various industries. With the ability to process vast amounts of data …

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 …