Arbel, M;
Zhou, L;
Gretton, A;
(2021)
Generalized Energy Based Models.
In:
Proceedings of the 9th International Conference on Learning Representations: ICLR 2021.
ICLR
Preview |
Text
1585_generalized_energy_based_model.pdf - Published Version Download (9MB) | Preview |
Abstract
We introduce the Generalized Energy Based Model (GEBM) for generative modelling. These models combine two trained components: a base distribution (generally an implicit model), 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"). GEBMs are trained by alternating between learning the energy and the base. We show that both training stages are well-defined: the energy is learned by maximising a generalized likelihood, and the resulting energy-based loss provides informative gradients for learning the base. Samples from the posterior on the latent space of the trained model can be obtained via MCMC, thus finding regions in this space that produce better quality samples. Empirically, the GEBM samples on image-generation tasks are of much better quality than those from the learned generator alone, indicating that all else being equal, the GEBM will outperform a GAN of the same complexity. When using normalizing flows as base measures, GEBMs succeed on density modelling tasks, returning comparable performance to direct maximum likelihood of the same networks.
Type: | Proceedings paper |
---|---|
Title: | Generalized Energy Based Models |
Event: | ICLR 2021 - 9th International Conference on Learning Representations |
Open access status: | An open access version is available from UCL Discovery |
Publisher version: | https://openreview.net/forum?id=0PtUPB9z6qK |
Language: | English |
Additional information: | This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions. |
UCL classification: | UCL UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neurosci Unit |
URI: | https://discovery-pp.ucl.ac.uk/id/eprint/10167377 |
Archive Staff Only
![]() |
View Item |