Taming Hyperparameter Tuning in Continuous Normalizing Flows Using the JKO Scheme

1 code implementation • 30 Nov 2022 • Alexander Vidal, Samy Wu Fung, Luis Tenorio, Stanley Osher, Levon Nurbekyan

Instead of tuning $\alpha$, we repeatedly solve the optimization problem for a fixed $\alpha$ effectively performing a JKO update with a time-step $\alpha$.

Density Estimation