Search Results
Search type | Search syntax |
---|---|
Tags | [tag] |
Exact | "words here" |
Author |
user:1234 user:me (yours) |
Score |
score:3 (3+) score:0 (none) |
Answers |
answers:3 (3+) answers:0 (none) isaccepted:yes hasaccepted:no inquestion:1234 |
Views | views:250 |
Code | code:"if (foo != bar)" |
Sections |
title:apples body:"apples oranges" |
URL | url:"*.example.com" |
Saves | in:saves |
Status |
closed:yes duplicate:no migrated:no wiki:no |
Types |
is:question is:answer |
Exclude |
-[tag] -apples |
For more details on advanced search visit our help page |
1
vote
Upper bound on the $p$-Wasserstein distance $\mathcal{W}_p(\xi,a\,\xi)$ for some constant $a...
There is a bound, the coupling $(\xi, a \xi)$ leads to the upper bound \begin{align*}
W_p(\xi, a \xi)^p &\leq \mathbb{E}[|\xi - a\xi|^p] = |(1-a)|^p \mathbb{E}[|\xi|^p]\\ \Rightarrow ~~~~ W_p(\xi, a\x …
1
vote
Building the Wasserstein space by pushforwards
Perhaps another simple argument that $\mathcal{X}$ is indeed equal to $\mathcal{W}_2(\mathbb{R}^d$):
Starting from the fact that there is a bimeasurable bijection $b : \mathbb{R}^d \rightarrow \mathbb …
2
votes
Accepted
Optimal transport for applied mathematicians: how does $\varphi (x) = \inf_{y \in Y} [c(x, y...
I hope I did not misunderstand the question, but it seems $\varphi(x) > - \infty$ holds as follows if $(x, y) \in \Gamma$:
For any $(x_i, y_i) \in \Gamma$, $i=1, \dots, n$, we see that
\begin{align}
…
1
vote
Invertibility of neural network as operator on Wasserstein space
This is just a partial answer regarding $S$ being injective.
The generalisation of your argument is given by Hornik (Theorem 5 and the definition of discriminatory functions above Theorem 5)
2
votes
Accepted
The largest Wasserstein distance to uniform distribution among all probability distributions...
I think I have an answer for the case p = 1, K = 2. I write "I think" because my computation does not coincide with the example values for $N=4$ posted earlier by OP in a comment, but I really cannot …
3
votes
Measurability of Markov kernel wrt the Borel $\sigma$-algebra generated by the weak topology
As already mentioned in the comments, this is really a standard result, see, e.g., Lemma 3.1. in Kallenberg's book.