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 …

We study the fundamental problem of transfer learning where a learning algorithm collects
data from some source distribution $ P $ but needs to perform well with respect to a different …

$$ The classical theory of statistical estimation aims to estimate a parameter of interest
under data generated from a fixed design (" offline estimation"), while the contemporary …

Multiclass classification is the simple generalization of binary classification to arbitrary label
sets. Despite its simplicity, it has been remarkably resistant to study: a characterization of …

We study the fundamental problem of sequential probability assignment, also known as
online learning with logarithmic loss, with respect to an arbitrary, possibly nonparametric …

Recent work on learning has yielded a striking result: the learnability of various problems
can be undecidable, or independent of the standard ZFC axioms of set theory. Furthermore …

Most work in the area of learning theory has focused on designing effective Probably
Approximately Correct (PAC) learners. Recently, other models of learning such as …

We consider the problem of multiclass transductive online learning when the number of
labels can be unbounded. Previous works by Ben-David et al.[1997] and Hanneke et …

We present novel reductions from sample compression schemes in multiclass classification,
regression, and adversarially robust learning settings to binary sample compression …