| Abstract: |
| The Wasserstein metric is a metric on the space of probability measures on a complete separable metric space.
Even on Euclidean space, the Wasserstein metric is not easy to compute except for the one-dimensional case.
To reduce the computational complexity, the sliced Wasserstein metric is introduced.
In this talk, I introduce a two-parameter family of metrics on Euclidean space, including the sliced Wasserstein metric.
I discuss its geometric properties emphasis on the difference from the Wasserstein metric.
This is joint work with Jun KITAGAWA (Michigan State University). |
|