Adrian Ciotinga
Computer science
Hometown: Phoenix, Arizona, United States
Graduation date: Spring 2025
Additional details: Honors student
FURI | Summer 2024
Computing the Optimal Transport Map Between Probabilistic Circuits
This work presents an algorithm for computing the globally optimal transport map between two probabilistic circuits (PCs) — known as the Wasserstein distance — which provides a natural way of comparing and interpolating PCs. Furthermore, while the complexity of computing this optimal transport map is NP-hard in general, this work shows that imposing small restrictions on the structure of the two PCs allows for computing a transport map that is globally optimal in polynomial time.
Mentor: YooJung Choi
It’s hip to be square.
Students presenting projects at the Fulton Forge Student Research Expo are encouraged to download this personal QR code and include it within your poster. This allows expo attendees to explore more about your project and about you in the future.
Right click the image to save it to your computer.