A Manifold Two-Sample Test Study: Integral Probability Metric with Neural Networks. (arXiv:2205.02043v1 [stat.ML])

Web: http://arxiv.org/abs/2205.02043

Two-sample tests are important areas aiming to determine whether two
collections of observations follow the same distribution or not. We propose
two-sample tests based on integral probability metric (IPM) for
high-dimensional samples supported on a low-dimensional manifold. We
characterize the properties of proposed tests with respect to the number of
samples $n$ and the structure of the manifold with intrinsic dimension $d$.
When an atlas is given, we propose two-step test to identify the difference
between general distributions, which achieves …

arxiv manifold ml networks neural neural networks probability study test