Live presentation at CAp'2021 by Marco Cuturi

Differentiating through Optimal Transport

Marco Cuturi

Computing or approximating an optimal transport cost is rarely the sole goal when using OT in applications. In most cases the end goal relies instead on solving the OT problem and studying the differentiable properties of its solutions w.r.t. to arbitrary inputs, be them points clouds in Euclidean spaces or points on a graph. I will present in this talk recent applications that highlight this necessity, as well as concrete algorithmic and programmatic solutions to handle such issues which have been implemented in Optimal Transport Tools (OTT), a python toolbox using JAX for differentiable programming.