Sampling from probability distributions is a crucial task in both statistics and machine learning. However, when the target distribution does not permit exact sampling, researchers often rely on Markov chain Monte Carlo (MCMC) methods.

Knowledge distillation is a popular approach for enhancing the performance of "student" models, with lower representational capacity, by taking advantage of

Three sampling techniques are presented for comparative investigations.

The fundamental problem of non-parametric two-sample testing consists in detecting the difference between any two distributions having access only to samples from these.

We also show that the network width alleviates these issues.