Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Questions about support sets for Wasserstein barycenters #367

Answered by rflamary
sandeshAdhikary asked this question in Q&A
Discussion options

Hello! Thank you all for all the great work on this excellent package!

I have a few questions regarding Wasserstein barycenter algorithms in POT. I am interested in computing Wasserstein barycenters of multiple empirical distributions such that (1) each distribution is defined over a different support set of samples and (2) the ground metric is arbitrary. Here are my questions:

  1. Are there any solvers in POT for free-support barycenters with respect to arbitrary ground metrics? The only free-support algorithm seems to be ot.lp.free_support_barycenter based on Algorithm 1 from this paper. But as far as I can tell, it does not allow for arbitrary ground metrics.

  2. Do all fixed-support Wasserstein barycenter solvers in POT assume that all input distributions (and the barycenter itself) are defined over the same support set? For instance, ot.barycenter only takes a single cost matrix as input, so I’m guessing this matrix should encode pairwise distances between samples in a single fixed support set. All distributions are then defined as histograms over the same support?

You must be logged in to vote
  1. There is for the moment no "general ground metrics" free_support_barycenter because the algorithm implemented is a block coordinate descent that requires a closed form solution for the update of the position which is not available for any losses. For general loss you can indeed implement a gradient descent form a sum of losses returned by ot.emd2 when using differentiable loss matrices.

  2. The ot.barycenterfunction supposes that the support for all the distributions in the barycenter is the same (because a ground cost matrix is necessary and the j index in M_i,j index the positions in the distributions) but the barycenter itself does not need to be the same support as the distributions (...

Replies: 1 comment 1 reply

Comment options

  1. There is for the moment no "general ground metrics" free_support_barycenter because the algorithm implemented is a block coordinate descent that requires a closed form solution for the update of the position which is not available for any losses. For general loss you can indeed implement a gradient descent form a sum of losses returned by ot.emd2 when using differentiable loss matrices.

  2. The ot.barycenterfunction supposes that the support for all the distributions in the barycenter is the same (because a ground cost matrix is necessary and the j index in M_i,j index the positions in the distributions) but the barycenter itself does not need to be the same support as the distributions (the ground metric need not be square and the i index can correspond to different positions on the barycenter).

You must be logged in to vote
1 reply
Comment options

Thank you! That clears things up

Answer selected by sandeshAdhikary
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet

AltStyle によって変換されたページ (->オリジナル) /