<ul data-eligibleForWebStory="true"><li>Explicit density learners are gaining popularity as generative models for their ability to model probability distributions, offering advantages over Generative Adversarial Networks.</li><li>Normalizing flows use bijective functions to make complex probability functions manageable, but can be challenging to train and may have lower sampling quality.</li><li>Novel knowledge distillation techniques are introduced to improve sampling quality and density estimation in smaller student normalizing flows.</li><li>The study explores knowledge distillation in Compositional Normalizing Flows, showing significant performance gains and increased throughput with smaller models.</li></ul>

Distilling Normalizing Flows

Discover more