Skip to main content
14 events
when toggle format what by license comment
Jun 18, 2022 at 10:14 history edited Martin Sleziak
added the tag (wasserstein-distance)
Jun 18, 2022 at 8:02 history edited Glorfindel CC BY-SA 4.0
broken link fixed, cf. https://math.meta.stackexchange.com/a/34713/228959
Aug 30, 2015 at 19:39 answer added VictorZurkowski timeline score: 4
Jun 4, 2013 at 12:51 vote accept Roberto Imbuzeiro Oliveira
Oct 2, 2010 at 10:30 answer added R W timeline score: 6
Oct 1, 2010 at 14:04 comment added Benoît Kloeckner That a probability measure $\mu$ on $\mathbb{R}^d$ is entirely defined by its projections on lines is more or less Radon's theorem. What you want is a quantitative version of this, you could therefore try to use the inversion formula for Radon transform: it gives you, at least when $\mu$ has a density, an expression of $\mu$ in terms of the $\mu_v$. However it seems difficult to relate this formula with the Wasserstein distance.
Oct 1, 2010 at 10:05 history edited Roberto Imbuzeiro Oliveira CC BY-SA 2.5
Corrected the formula for W.
Oct 1, 2010 at 10:04 comment added Roberto Imbuzeiro Oliveira Thanks! I guess I had the dual definition in mind when writing this.
Oct 1, 2010 at 8:51 comment added Florian There is an error in your definition of the Wasserstein metric: you have to replace inf by sup.
Sep 7, 2010 at 23:33 history edited Roberto Imbuzeiro Oliveira CC BY-SA 2.5
Corrected typo.
Sep 4, 2010 at 11:40 comment added Mark Meckes I don't have time to think about your question at the moment, but you may be interested in the results for typical $d$-dimensional projections here: arxiv.org/abs/0912.2044
Sep 4, 2010 at 3:28 history edited Roberto Imbuzeiro Oliveira CC BY-SA 2.5
Minor rephrasing of first sentence.
Sep 4, 2010 at 0:55 history edited Roberto Imbuzeiro Oliveira CC BY-SA 2.5
Corrected spelling
Sep 4, 2010 at 0:46 history asked Roberto Imbuzeiro Oliveira CC BY-SA 2.5