Autoregressive Diffusion Models

Add to your list(s) Download to your calendar using vCal

• Emiel Hoogeboom
• Wednesday 30 March 2022, 11:00-12:30
• Cambridge University Engineering Department, CBL Seminar room BE4-38.

If you have a question about this talk, please contact Elre Oldewage.

Autoregressive diffusion models are a new generative model that can be seen as an autoregressive model that places a distribution over variables in random dimension order. In this talk we will discuss their relation to standard (Gaussian-based) diffusion models, and the lessons (positive and negative) we can draw from this project.

Recommended reading: the original ‘modern’ diffusion paper (DDPMs) at https://arxiv.org/abs/2006.11239

Bio: Emiel is a last year PhD candidate at the University of Amsterdam under the supervision of Max Welling. Research interests include generative modelling and variational inference, for instance focusing on discrete variable extensions. He completed a BSc in Aerospace Engineering and a MSc in Artificial Intelligence. After a 3 month sabbatical he will join Google Brain in Amsterdam.

This talk is part of the Machine Learning Reading Group @ CUED series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge University Engineering Department Talks
• Cambridge University Engineering Department, CBL Seminar room BE4-38
• Cambridge talks
• Centre for Smart Infrastructure & Construction
• Chris Davis' list
• Computational Continuum Mechanics Group Seminars
• Featured lists
• Guy Emerson's list
• Hanchen DaDaDash
• Inference Group Journal Clubs
• Inference Group Summary
• Information Engineering Division seminar list
• Interested Talks
• ML
• Machine Learning Reading Group
• Machine Learning Reading Group @ CUED
• Machine Learning Summary
• Quantum Matter Journal Club
• Required lists for MLG
• School of Technology
• Simon Baker's List
• TQS Journal Clubs
• Trust & Technology Initiative - interesting events
• bld31
• custom
• ndk22's list
• ob366-ai4er
• rp587
• yk373's list

Note that ex-directory lists are not shown.