This monograph portrays optimization as a process. In many practical applications the
environment is so complex that it is infeasible to lay out a comprehensive theoretical model …

KNN classification is an improvisational learning mode, in which they are carried out only
when a test data is predicted that set a suitable K value and search the K nearest neighbors …

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 extend the classical theory of PAC learning in a way which allows to model a rich variety
of practical learning tasks where the data satisfy special properties that ease the learning …

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 show that a recently proposed 1-nearest-neighbor-based multiclass learning algorithm
is universally strongly Bayes consistent in all metric spaces where such Bayes consistency …

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 …

Adversarially robust machine learning has received much recent attention. However, prior
attacks and defenses for non-parametric classifiers have been developed in an ad-hoc or …

A growing body of research has shown that many classifiers are susceptible to adversarial
examples–small strategic modifications to test inputs that lead to misclassification. In this …

We analyze a family of supervised learning algorithms based on sample compression
schemes that are stable, in the sense that removing points from the training set which were …