1. Strong equivalence between metrics of Wasserstein type
- Author
-
Gaoyue Guo and Erhan Bayraktar
- Subjects
Statistics and Probability ,Discrete mathematics ,Probability (math.PR) ,Duality (mathematics) ,Type (model theory) ,46N30, 60A99 ,Functional Analysis (math.FA) ,Mathematics - Functional Analysis ,Wasserstein metric ,FOS: Mathematics ,Statistics, Probability and Uncertainty ,Equivalence (measure theory) ,Mathematics - Probability ,Mathematics ,Curse of dimensionality - Abstract
The sliced Wasserstein and more recently max-sliced Wasserstein metrics $\mW_p$ have attracted abundant attention in data sciences and machine learning due to its advantages to tackle the curse of dimensionality. A question of particular importance is the strong equivalence between these projected Wasserstein metrics and the (classical) Wasserstein metric $\Wc_p$. Recently, Paty and Cuturi have proved the strong equivalence of $\mW_2$ and $\Wc_2$. We show that the strong equivalence also holds for $p=1$, while we show that the sliced Wasserstein metric does not share this nice property., Comment: To appear in Electronic Communications in Probability
- Published
- 2021