Explore a 50-minute lecture by Giulia Luise of Microsoft on "Learning to optimize transport plans" presented at IPAM's Statistical and Numerical Methods for Non-commutative Optimal Transport Workshop at UCLA on May 19, 2025. Begin with a brief introduction to entropy-regularized optimal transport, a powerful tool for comparing probability measures that has proven successful in machine learning applications. Dive into the concept of 'learning to optimize' transport plans by leveraging amortized optimization. This presentation covers joint research work conducted with Brandon Amos (META), Samuel Cohen (UCL), and Ievgen Redko (Aalto University). For more information about this workshop and related programs, visit the IPAM UCLA website.