Presenters: Stratis Markou and James Allingham (University of Cambridge)
Abstract: While the log-likelihood of the data is analytic in many familiar machine learning models, there exist certain models, called Energy Based Models (EBMs), for which the log-likelihood is intractable. Lifting the restriction of a tractable log-likelihood opens the door to great flexibility in model architecture and design, but naturally complicates training. In this presentation, we provide an overview of both established as well as recently developed methods for training EBMs.
Reading list: How to train your energy based model (https://arxiv.org/pdf/2101.03288.pdf)