[WIP] Add backend dual loss and plan computation for stochastic optimization or regularized OT by rflamary · Pull Request #360 · PythonOT/POT
Types of changes
Motivation and context / Related issue
Add differentiable losses for stochastic optimization of entropic and quadratic OT and functions to recover the OT plkan thanks to the primal-dual relations.
Adds two exmapels of use of those functions:
- Dual OT solvers for entropic and quadratic regularized OT with Pytorch
- Continuous OT plan estimation with Pytorch
How has this been tested (if it applies)
PR checklist
- I have read the CONTRIBUTING document.
- The documentation is up-to-date with the changes I made (check build artifacts).
- All tests passed, and additional code has been covered with new tests.
- I have added the PR and Issue fix to the RELEASES.md file.