NYU Computer Science · Fall 2026
This seminar course explores how to match and transform probability distributions for machine learning applications. The course begins with a few lectures on optimal transport and flow matching, and transitions into a reading group covering contemporary methods and applications across scientific domains.
Topics include: Wasserstein distances and optimal transport, entropic regularization, Sinkhorn algorithm, continuous normalizing flows, conditional flow matching, Schrödinger bridges, and applications in single-cell biology, molecular generation, and image synthesis.
Open to graduate students with a background in probability and statistics at the level of a graduate ML course.