v0.2.0

We're happy to announce the 0.2.0 release.

We add two end-to-end predict-then-optimize methods with stochastical perturbation: Differentiable Perturbed Optimizers and Fenchel-Young loss with Perturbation into our package "PyEPO."

People now are allowed to use PyTorch module pyepo.func.perturbedOpt and pyepo.func.perturbedFenchelYoung. See details in our docs.

Both approaches come from Google Research's awesome project Differentiable Optimizers with Perturbations in Tensorflow, and there is the corresponding paper Learning with differentiable perturbed optimizers.

Initial Release

We're happy to announce the 0.1.0 release.
It's the first release version of "PyEPO".