Title:
Generalized Energy-Based Models
Generalized Energy-Based Models
dc.contributor.author | Gretton, Arthur | |
dc.contributor.corporatename | Georgia Institute of Technology. Machine Learning | en_US |
dc.contributor.corporatename | University College London. Centre for Computational Statistics and Machine Learning (CSML) | en_US |
dc.date.accessioned | 2021-10-20T20:02:44Z | |
dc.date.available | 2021-10-20T20:02:44Z | |
dc.date.issued | 2021-10-13 | |
dc.description | Presented online via Bluejeans Events on October 13, 2021 at 12:00 p.m. | en_US |
dc.description | Arthur 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.description | Runtime: 63:40 minutes | en_US |
dc.description.abstract | Arthur 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.extent | 63:40 minutes | |
dc.identifier.uri | http://hdl.handle.net/1853/65392 | |
dc.language.iso | en_US | en_US |
dc.relation.ispartofseries | Machine Learning @ Georgia Tech (ML@GT) Seminar Series | |
dc.subject | Energy-based models | en_US |
dc.subject | Generative models | en_US |
dc.subject | Implicit models | en_US |
dc.subject | Probability divergences | en_US |
dc.title | Generalized Energy-Based Models | en_US |
dc.type | Moving Image | |
dc.type.genre | Lecture | |
dspace.entity.type | Publication | |
local.contributor.corporatename | Machine Learning Center | |
local.contributor.corporatename | College of Computing | |
local.relation.ispartofseries | ML@GT Seminar Series | |
relation.isOrgUnitOfPublication | 46450b94-7ae8-4849-a910-5ae38611c691 | |
relation.isOrgUnitOfPublication | c8892b3c-8db6-4b7b-a33a-1b67f7db2021 | |
relation.isSeriesOfPublication | 9fb2e77c-08ff-46d7-b903-747cf7406244 |
Files
Original bundle
1 - 4 of 4
No Thumbnail Available
- Name:
- gretton.mp4
- Size:
- 207.57 MB
- Format:
- MP4 Video file
- Description:
- Download video
No Thumbnail Available
- Name:
- gretton_videostream.html
- Size:
- 1.32 KB
- Format:
- Hypertext Markup Language
- Description:
- Streaming video
No Thumbnail Available
- Name:
- transcript.txt
- Size:
- 52.13 KB
- Format:
- Plain Text
- Description:
- Transcription
- Name:
- thumbnail.jpg
- Size:
- 52.14 KB
- Format:
- Joint Photographic Experts Group/JPEG File Interchange Format (JFIF)
- Description:
- Thumbnail
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 3.13 KB
- Format:
- Item-specific license agreed upon to submission
- Description: