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 …
I Attias, S Hanneke - International Conference on Machine …, 2023 - proceedings.mlr.press
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 …