diff options
author | RĂ©mi Flamary <remi.flamary@gmail.com> | 2021-11-04 11:00:09 +0100 |
---|---|---|
committer | GitHub <noreply@github.com> | 2021-11-04 11:00:09 +0100 |
commit | 2fe69eb130827560ada704bc25998397c4357821 (patch) | |
tree | 82973444cc4afc4c42cc7cdaf43a2ebd4b1a6a91 /README.md | |
parent | 9c6ac880d426b7577918b0c77bd74b3b01930ef6 (diff) |
[MRG] Make gromov loss differentiable wrt matrices and weights (#302)
* grmov differentable
* new stuff
* test gromov gradients
* fgwdifferentiable
* fgw tested
* correc name test
* add awesome example with gromov optimizatrion
* pep8+ typos
* damn pep8
* thunbnail
* remove prints
Diffstat (limited to 'README.md')
-rw-r--r-- | README.md | 9 |
1 files changed, 6 insertions, 3 deletions
@@ -26,7 +26,7 @@ POT provides the following generic OT solvers (links to examples): * Debiased Sinkhorn barycenters [Sinkhorn divergence barycenter](https://pythonot.github.io/auto_examples/barycenters/plot_debiased_barycenter.html) [37] * [Smooth optimal transport solvers](https://pythonot.github.io/auto_examples/plot_OT_1D_smooth.html) (dual and semi-dual) for KL and squared L2 regularizations [17]. * Non regularized [Wasserstein barycenters [16] ](https://pythonot.github.io/auto_examples/barycenters/plot_barycenter_lp_vs_entropic.html)) with LP solver (only small scale). -* [Gromov-Wasserstein distances](https://pythonot.github.io/auto_examples/gromov/plot_gromov.html) and [GW barycenters](https://pythonot.github.io/auto_examples/gromov/plot_gromov_barycenter.html) (exact [13] and regularized [12]) +* [Gromov-Wasserstein distances](https://pythonot.github.io/auto_examples/gromov/plot_gromov.html) and [GW barycenters](https://pythonot.github.io/auto_examples/gromov/plot_gromov_barycenter.html) (exact [13] and regularized [12]), differentiable using gradients from * [Fused-Gromov-Wasserstein distances solver](https://pythonot.github.io/auto_examples/gromov/plot_fgw.html#sphx-glr-auto-examples-plot-fgw-py) and [FGW barycenters](https://pythonot.github.io/auto_examples/gromov/plot_barycenter_fgw.html) [24] * [Stochastic solver](https://pythonot.github.io/auto_examples/plot_stochastic.html) for Large-scale Optimal Transport (semi-dual problem [18] and dual problem [19]) * [Stochastic solver of Gromov Wasserstein](https://pythonot.github.io/auto_examples/gromov/plot_gromov.html) for large-scale problem with any loss functions [33] @@ -295,5 +295,8 @@ You can also post bug reports and feature requests in Github issues. Make sure t via optimal transport and diffusions](http://proceedings.mlr.press/v97/liutkus19a/liutkus19a.pdf). In International Conference on Machine Learning (pp. 4104-4113). PMLR. -[37] Janati, H., Cuturi, M., Gramfort, A. Proceedings of the 37th International -Conference on Machine Learning, PMLR 119:4692-4701, 2020
\ No newline at end of file +[37] Janati, H., Cuturi, M., Gramfort, A. [Debiased sinkhorn barycenters](http://proceedings.mlr.press/v119/janati20a/janati20a.pdf) Proceedings of the 37th International +Conference on Machine Learning, PMLR 119:4692-4701, 2020 + +[38] C. Vincent-Cuaz, T. Vayer, R. Flamary, M. Corneli, N. Courty, [Online Graph +Dictionary Learning](https://arxiv.org/pdf/2102.06555.pdf), International Conference on Machine Learning (ICML), 2021.
\ No newline at end of file |