[IDA ML Seminar] Machine Learning Seminar, 8/11 at 15:15: Brooks Paige, UCL, "Moment matching denoising Gibbs sampling"

[Fredrik Lindsten]

Welcome to an IDA Machine Learning Seminar on Wednesday, November 8 at 15:15 in Ada Lovelace

Moment matching denoising Gibbs sampling
Brooks Paige<https://tbrx.github.io/>, Associate Professor, University College London

Abstract: Energy-based models offer a versatile framework for modeling complex data distributions. However, training and sampling from energy-based models poses significant challenges. The widely-used denoising score matching method for training energy-based models suffers from inconsistency issues, causing the energy model to learn a `noisy' data distribution. In this talk I will describe a proposal for an alternative sampling framework, (pseudo)-Gibbs sampling with moment matching, which enables effective sampling from the underlying clean model when given a `noisy' model trained via denoising score matching. We explore the benefits of the approach compared to related methods, how to scale to high-dimensional data, and connections to diffusion models.

Location: Ada Lovelace, https://www.ida.liu.se/department/location/search.en.shtml?keyword=ada

------------------

The list of future seminars in the series is available at: http://www.ida.liu.se/research/machinelearning/seminars/
You can subscribe to the seminar series' calendar using this ics link: https://outlook.office365.com/owa/calendar/4d811ae47ce446f58d11a7c2f50a7ed8@ad.liu.se/0f5253d7bc7841248c71eb4c28eb2d668927992292494627279/calendar.ics





-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.liu.se/pipermail/ml-seminars/attachments/20231102/9c5dd9ae/attachment.htm>