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


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.

  • 1
    $\begingroup$ Interested in this question as well... $\endgroup$
    – Kashif
    Jan 24, 2018 at 21:51
  • $\begingroup$ Are you interested in explicit formulas for normal distributions only, or for other specific measures as well? $\endgroup$ Nov 9, 2018 at 15:02

1 Answer 1


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.

  • 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, 2020 at 20:47
  • $\begingroup$ Fixed. Thanks for pointing it out $\endgroup$
    – Meni
    Jan 20, 2020 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.