We study computational aspects of algorithmic replicability, a notion of stability introduced by
Impagliazzo, Lei, Pitassi, and Sorrell [2022]. Motivated by a recent line of work that …

We give an algorithm for testing uniformity of distributions supported on hypergrids [m
1]×···×[mn], which makes many queries to a subcube conditional sampling oracle with m …

A foundational goal of machine learning theory is to characterize the inherent computational
and statistical complexity of some of the most basic tasks in machine learning. In this thesis …