When two different parties use the same learning rule on their own data, how can we test
whether the distributions of the two outcomes are similar? In this paper, we study the …

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 …

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 …

The quintessential learning algorithm of empirical risk minimization (ERM) is known to fail in
various settings for which uniform convergence does not characterize learning. Relatedly …

Specifying all desirable properties of a language model is challenging, but certain
requirements seem essential. Given samples from an unknown language, the trained model …

A classical result in learning theory shows the equivalence of PAC learnability of binary
hypothesis classes and the finiteness of VC dimension. Extending this to the multiclass …

This work continues to investigate the link between differentially private (DP) and online
learning. Alon, Livni, Malliaris, and Moran [4] showed that for binary concept classes, DP …

We study universal rates for multiclass classification, establishing the optimal rates (up to log
factors) for all hypothesis classes. This generalizes previous results on binary classification …

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 …

The well-known empirical risk minimization (ERM) principle is the basis of many widely used
machine learning algorithms, and plays an essential role in the classical PAC theory. A …