21
$\begingroup$

The $p$-Wasserstein between two measures $\nu_1$ and $\nu_2$ on $X$ is given by

$$d_p(\nu_{1},\nu_{2})=\underset{\pi\in\Gamma(\nu_{1},\nu_{2})}{\inf}\int_{\mathbf{\mathcal{X}}^{2}}d(x,y)^p\pi(dx,dy)$$

where $\Gamma(\nu_{1},\nu_{2})$ is the set of all couplings between $\nu_1$ and $\nu_2$. For $X=\mathbb{R}^d$ and $d$ being the euclidean distance the optimal transport between $\nu_{1}=N(m,V)$ and $\nu_{2}=N(n,U)$ is well known for $p=2$ see e.g. On Wasserstein geometry of the space of Gaussian measures by Asuka Takatsu. However what is known for $p=1$ for the Euclidean distance or other "reasonable" metrics? I am interested in explicit formulas or sharp bounds.

| cite | improve this question | | | | |
$\endgroup$
  • 1
    $\begingroup$ Interested in this question as well... $\endgroup$ – Glassjawed Jan 24 '18 at 21:51
  • $\begingroup$ Are you interested in explicit formulas for normal distributions only, or for other specific measures as well? $\endgroup$ – leo monsaingeon Nov 9 '18 at 15:02
2
$\begingroup$

For $p=1$ one can bound the 1-Wasserstein metric by $$|m-n| + \sqrt{\sum_{i=1}^{d} \left[ \left( \sqrt{\lambda_i} - \sqrt{\gamma_i}\right)^2 + 2\sqrt{\lambda_i\gamma_i}(1-v_i\cdot u_i) \right]}$$

when $\lambda_i$ and $\gamma_i$ are the $i^{th}$ eigen values of $U$ and $V$ respectively, $v_1,\ldots,v_d$ and $u_1,\ldots,u_d$ are the corresponding orthonormal basis of eigen-vectors.

See Chafai & Malrieu Lemma 2.4.

Although this bound seems close-in nature to the $p=2$ bound, I'm not sure if it is sharp.

| cite | improve this answer | | | | |
$\endgroup$
  • 1
    $\begingroup$ There is a typo in your bound. The "$uv$" term should be $(1-v_i\cdot u_i)$. Also, note that this bound is an equality when the covariance matrices are equal (infact in this case all $W_p(\nu_1,\nu_2) = \|m-n\|_2$ for all $p \ge 1$). $\endgroup$ – dohmatob Jan 19 at 20:47
  • $\begingroup$ Fixed. Thanks for pointing it out $\endgroup$ – Meni Jan 20 at 6:33

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.