The central limit theorem (CLT) is one of the most fundamental results i...
Estimating optimal dynamic policies from offline data is a fundamental
p...
The central limit theorem is one of the most fundamental results in
prob...
Concentration inequalities for the sample mean, like those due to Bernst...
Estimation and inference on causal parameters is typically reduced to a
...
We provide results that exactly quantify how data augmentation affects t...
Network data are ubiquitous in modern machine learning, with tasks of
in...
One of the most commonly used methods for forming confidence intervals f...
Cross validation is a central tool in evaluating the performance of mach...
Empirical risk minimization is the principal tool for prediction problem...
We consider random processes whose distribution satisfies a symmetry
pro...
Modern neural networks are highly overparameterized, with capacity to
su...