Session III.3 - Computational Optimal Transport
Tuesday, June 20, 18:00 ~ 18:30
Learning to optimize transport plans
Giulia Luise
Microsoft Research - This email address is being protected from spambots. You need JavaScript enabled to view it.
Optimal transport distances and their regularized versions are a powerful tool to compare probability measures, that proved successful in many machine learning applications. In this talk, I will give a brief introduction on (entropy-regularized) optimal transport and dive into 'learning to optimize' transport plans leveraging amortized optimization.
Joint work with Brandon Amos (META), Samuel Cohen (UCL), Ievgen Redko (Aalto University).