Monday, November 30, 2020
11/30/2020 - 2:30pm
Abstract: I will introduce Generalized Energy Based Models (GEBM) for generative modelling. These models combine two trained components: a base distribution (generally an implicit model, as in a Generative Adversarial Network), which can learn the support of data with low intrinsic dimension in a high dimensional space; and an energy function, to refine the probability mass on the learned support. Both the energy function and base jointly constitute the final model, unlike GANs, which retain only the base distribution (the “generator”). In particular, while the energy function is analogous to the GAN critic function, it is not discarded after training.
Zoom Meeting ID: 97670014308
11/30/2020 - 4:00pm
Duke-Rudnick-Sarnak and Eskin-McMullen initiated the use of