Adversarial data augmentation has shown promise for training robust deep neural networks
against unforeseen data shifts or corruptions. However, it is difficult to define heuristics to …

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 …

Mutual information is a general statistical dependency measure which has found
applications in representation learning, causality, domain generalization and computational …

The statistical analysis of discrete data has been the subject of extensive statistical research
dating back to the work of Pearson. In this survey we review some recently developed …

For decades, statisticians have studied the species problem: how to estimate the total
number of species, observed plus unobserved, in a population. This problem dates at least …

Estimation of mutual information from observed samples is a basic primitive in machine
learning, useful in several learning tasks including correlation mining, information …

We propose a general methodology for the construction and analysis of essentially minimax
estimators for a wide class of functionals of finite dimensional parameters, and elaborate on …

Do GANS (Generative Adversarial Nets) actually learn the target distribution? The
foundational paper of Goodfellow et al.(2014) suggested they do, if they were given …

Property testing is concerned with the design of super-fast algorithms for the structural
analysis of large quantities of data. The aim is to unveil global features of the data, such as …

Consider the problem of estimating the Shannon entropy of a distribution over elements from
independent samples. We show that the minimax mean-square error is within the universal …