This question is inspired by this much older question:

Convergence of an empirical distribution w.r.t. the Hellinger distance

Let $P$ be a continuous probability distribution on a compact subset of $\mathbb{R}^3$ and let $X_1,X_2,…,X_n$ be drawn i.i.d. according to $P$. Define the empirical distribution: $$\hat{P_n}(x) = \frac{1}{n} \sum_{i=1}^{n} 1_{X_i = x}$$

Let $d(P,Q)$ denote the earth-mover distance between two distributions $P$ and $Q$. Is there a nice expression for the expected distance between $\hat{P_n}$ and $P$?


See, e.g., section 2.1 of http://arxiv.org/pdf/1209.1077.pdf; also http://dx.doi.org/10.1007/BF02213456, which is cited in Villani's book as having particularly precise estimates.

| cite | improve this answer | |
  • $\begingroup$ Looking at the paper you cite, it seems that that paper cites an earlier work for the $W_1$ distance, which I think is the "earth-mover distance": [11] V. Dobri and J. Yukich. Asymptotics for transportation cost in high dimensions. Journal of Theoretical Probability, 8:97-118, 1995. $\endgroup$ – Anthony Quas Nov 6 '14 at 18:16

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.