BITESIZE | How Do Diffusion Models Work?
Learning Bayesian Statistics · Alexandre Andorra
Audio is streamed directly from the publisher (api.riverside.fm) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
Today's clip is from Episode 151 of the podcast, with Jonas Arruda
In this conversation, Jonas Arruda explains how diffusion models generate data by learning to reverse a noise process. The idea is to start from a simple distribution like Gaussian noise and gradually remove noise until the target distribution emerges. This is done through a forward process that adds noise to clean parameters and a backward process that learns how to undo that corruption. A noise schedule controls how much noise is added or removed at each step, guiding the transformation from pure randomness back to meaningful structure.
Get the full discussion here
• Join this channel to get access to perks:
https://www.patreon.com/c/learnbayesstats
• Intro to Bayes Course (first 2 lessons free): https://topmate.io/alex_andorra/503302
• Advanced Regression Course (first 2 lessons free): https://topmate.io/alex_andorra/1011122
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !