Optimal Transport - Entropic Regularisation
HTML-код
- Опубликовано: 11 сен 2024
- Math 707: Optimal Transport
Entropic Regularisation
October 30, 2019
This is a lecture on "Entropic Regularisation" given as a part of Brittany Hamfeldt's class Math 707: Optimal Transport at New Jersey Institute of Technology.
Syllabus: m.njit.edu/Gra...
This recorded lecture was supported by NSF DMS-1751996.
Doctor Hamfeldt please be aware this lecture series, for free, on youtube, is an absolute godsend! I will forever be thankful
Very nice lecture! I haven't seen the alternate characterization of the regularized OT in terms of minimizing KL with the Gibbs distribution before. Really cool!
very nice lecture. thank you for sharing!
Thank you so much for the lectures professor. I just needed to ask about the part at 20:42. How is \pi sparse in that case?
Keep in mind that \pi is defined on the product space X x Y. So in a simple example where X = Y = R, we have \pi defined on R^2. If the optimal map is a shift, say T(x) = x + a, then \pi is going to be supported on points of the form (x, x+a), which is a line. At any other points (x,y) in two-dimensions, no mass from x is transported to the point y, so \pi is zero around these points. Conclusion: all of the mass in \pi lives on a line in 2D, so \pi is sparse.
@@brittanyhamfeldt Thank you so much. I got it.