Normalized quantiles of Wasserstein distance to the empirical measure on [0,1] are asymptotically maximized for specific mixtures of two-point and uniform distributions, enabling explicit confidence regions.
Constructive quantization: Ap- proximation by empirical measures
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.PR 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bounding quantiles of Wasserstein distance between true and empirical measure
Normalized quantiles of Wasserstein distance to the empirical measure on [0,1] are asymptotically maximized for specific mixtures of two-point and uniform distributions, enabling explicit confidence regions.