We focus on some specific problems in distribution testing, taking goodness-of-fit as a
running example. In particular, we do not aim to provide a comprehensive summary of all the …

Energy-based models (EBMs) allow flexible specifications of probability distributions.
However, sampling from EBMs is non-trivial, usually requiring approximate techniques such …

Social media platforms (SMPs) leverage algorithmic filtering (AF) as a means of selecting
the content that constitutes a user's feed with the aim of maximizing their rewards …

We investigate the statistical task of closeness (or equivalence) testing for multidimensional
distributions. Specifically, given sample access to two unknown distributions p, q on d, we …

Abstract Goldwasser et al.(2021) recently proposed the setting of PAC verification, where a
hypothesis (machine learning model) that purportedly satisfies the agnostic PAC learning …

We focus on some specific problems in distribution testing, taking goodness-of-fit as a
running example. In particular, we do not aim to provide a comprehensive summary of all the …

We study the problem of learning under arbitrary distribution shift, where the learner is
trained on a labeled set from one distribution but evaluated on a different, potentially …

We consider the problem of hypothesis testing for discrete distributions. In the standard
model, where we have sample access to an underlying distribution $ p $, extensive research …

Uniformity testing is arguably one of the most fundamental distribution testing problems.
Given sample access to an unknown distribution $\mathbf {p} $ on $[n] $, one must decide if …

The framework of distribution testing is currently ubiquitous in the field of property testing. In
this model, the input is a probability distribution accessible via independently drawn …