Abstract
AbstractIn this note, we show that the squared Wasserstein distance can be expressed as the average over the sphere of one dimensional Wasserstein distances. We name this new expression for the Wasserstein Distance Radiant Formula. Using this formula, we are able to highlight new connections between the Wasserstein distances and the Sliced Wasserstein distance, an alternative Wasserstein-like distance that is cheaper to compute.
Publisher
Springer Science and Business Media LLC
Reference25 articles.
1. Kantorovich, L.V.: On the translocation of masses. J. Math. Sci. 133(4), 1381–1382 (2006)
2. Solomon, J., De Goes, F., Peyré, G., Cuturi, M., Butscher, A., Nguyen, A., Du, T., Guibas, L.: Convolutional wasserstein distances: Efficient optimal transportation on geometric domains. ACM Trans. Gr. (ToG) 34(4), 1–11 (2015)
3. Gangbo, W., McCann, R.J.: Shape recognition via wasserstein distance. Q. Appl. Math. 705–737 (2000)
4. Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: Proceedings of the 34th International Conference on Machine Learning, pp. 214–223 (2017)
5. Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Generative image inpainting with contextual attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5505–5514 (2018)