You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: RELEASES.md
+7Lines changed: 7 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,6 +2,12 @@
2
2
3
3
## 0.9.6
4
4
5
+
*September 2025*
6
+
7
+
This new release contains several new features and bug fixes. Among the new features we have a new submodule `ot.batch` that contains batch parallel solvers for several OT problems including [Sinkhorn, Gromov-Wasserstein and Fused Gromov-Wasserstein](https://pythonot.github.io/master/auto_examples/backends/plot_ot_batch.html). This new submodule can be used to solve many independent OT problems in parallel on CPU or GPU with shared source and target support sizes. We also implemented a new Nystrom kernel approximation for the Sinkhorn solver that can be used to speed up the computation of the Sinkhorn divergence on large datasets. We also added new 1D solvers for [Linear circular OT](https://pythonot.github.io/master/auto_examples/sliced-wasserstein/plot_compute_wasserstein_circle.html) and new solvers for free support [OT barycenters with generic cost functions](https://pythonot.github.io/master/auto_examples/barycenters/plot_free_support_barycenter_generic_cost.html) and for [barycenters between Gaussian Mixture Models (GMMs)](https://pythonot.github.io/master/auto_examples/barycenters/plot_gmm_barycenter.html). We also implemented two solvers for partial Fused Gromov-Wasserstein problems based on [conditional gradient](https://pythonot.github.io/master/gen_modules/ot.gromov.html#ot.gromov.partial_fused_gromov_wasserstein) and [projected gradient](https://pythonot.github.io/master/gen_modules/ot.gromov.html#ot.gromov.entropic_partial_fused_gromov_wasserstein) descents.
8
+
9
+
Finally we have updated the documentation to reflect the new generic API and reorganized the [examples gallery](https://pythonot.github.io/auto_examples/index.html).
10
+
5
11
#### New features
6
12
- Implement CG solvers for partial FGW (PR #687)
7
13
- Added feature `grad=last_step` for `ot.solvers.solve` (PR #693)
@@ -44,6 +50,7 @@
44
50
- Avoid raising unnecessary warnings in `ot.lp.solver_1d.binary_search_circle` (Issue #738)
45
51
- Avoid deprecation warning in `ot.lp.solver_1d.wasserstein_1d` (Issue #760, PR #761)
0 commit comments