Eric Jang: Tips for Training Likelihood Models
blog.evjang.com · 4,575 words · saved by 1 readers
This is a tutorial on common practices in training generative models that optimize likelihood directly, such as autoregressive models and ...
This is a tutorial on common practices in training generative models that optimize likelihood directly, such as autoregressive models and normalizing flows. Deep generative modeling is a fast-moving field, so I hope for this to be a newcomer-friendly introduction to the basic evaluation terminology used consistently across research papers, especially when it comes to modeling more complicated distributions like RGB images. This is a more in-depth version of the tutorial lecture I gave on normalizing flows at ICML. This tutorial discusses the most mathematically straightforward of generative…
saved by
related reading
- How Can We Make Robotics More like Generative Modeling? | Eric Jangevjang.com
- What are Diffusion Models? | Lil'Loglilianweng.github.io
- Just Ask for Generalization | Eric Jangevjang.com
- Generative modelling in latent space – Sander Dielemansander.ai
- Musings on typicality – Sander Dielemansander.ai
- Six (and a half) intuitions for KL divergence — LessWronglesswrong.com
- Generative Modeling by Estimating Gradients of the Data Distribution | Yang Songyang-song.github.io
- Approximating KL Divergencejoschu.net
- Normalizing flowsbehindml.com
- [1809.09087] Implicit Maximum Likelihood Estimationarxiv.org
- Denoising Density Estimatorsarxiv.org
- Generative Modeling by Estimating Gradients of the Data Distribution | Yang Songyang-song.github.io