Show simple item record

dc.contributor.authorGretton, Arthur
dc.date.accessioned2021-10-20T20:02:44Z
dc.date.available2021-10-20T20:02:44Z
dc.date.issued2021-10-13
dc.identifier.urihttp://hdl.handle.net/1853/65392
dc.descriptionPresented online via Bluejeans Events on October 13, 2021 at 12:00 p.m.en_US
dc.descriptionArthur Gretton is a Professor with the Gatsby Computational Neuroscience Unit, and director of the Centre for Computational Statistics and Machine Learning (CSML) at UCL. Arthur's recent research interests in machine learning include the design and training of generative models, both implicit (e.g. GANs) and explicit (exponential family and energy-based models), causal modeling, and nonparametric hypothesis testing.en_US
dc.descriptionRuntime: 63:40 minutesen_US
dc.description.abstractArthur Gretton will describe Generalized Energy Based Models (GEBM) for generative modeling. 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"). Furthermore, unlike classical energy-based models, the GEBM energy is defined even when the support of the model and data do not overlap. Samples from the trained model can be obtained via Langevin diffusion-based methods (MALA, UAL, HMC). Empirically, the GEBM samples on image-generation tasks are of 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.en_US
dc.format.extent63:40 minutes
dc.language.isoen_USen_US
dc.relation.ispartofseriesML@GT Seminar Series;
dc.subjectEnergy-based modelsen_US
dc.subjectGenerative modelsen_US
dc.subjectImplicit modelsen_US
dc.subjectProbability divergencesen_US
dc.titleGeneralized Energy-Based Modelsen_US
dc.typeLectureen_US
dc.typeVideoen_US
dc.contributor.corporatenameGeorgia Institute of Technology. Machine Learningen_US
dc.contributor.corporatenameUniversity College London. Centre for Computational Statistics and Machine Learning (CSML)en_US


Files in this item

Thumbnail
Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record