As discussed for instance in this tutorial, the (blurry) optimal transport plan "π_ij" is encoded in the dual vectors (potentials) computed by the GeomLoss solver. (See e.g. Gabriel Peyré's book or my PhD thesis, available in January, for more details.)
### May I ask how to obtain both the loss and the transport plan at the same time? I mean easily, without complex computation for the unbalanced debiased Sinkhorn divergence
As discussed for instance in this tutorial, the (blurry) optimal transport plan "π_ij" is encoded in the dual vectors (potentials) computed by the GeomLoss solver. (See e.g. Gabriel Peyré's book or my PhD thesis, available in January, for more details.)
### May I ask how to obtain both the loss and the transport plan at the same time? I mean easily, without complex computation for the unbalanced debiased Sinkhorn divergence