flâneur — a map of the web's best reading

Musings on typicality – Sander Dieleman

sander.ai · 5,108 words · saved by 2 readers

A summary of my current thoughts on typicality, and its relevance to likelihood-based generative models.

If you’re training or sampling from generative models, typicality is a concept worth understanding. It sheds light on why beam search doesn’t work for autoregressive models of images, audio and video; why you can’t just threshold the likelihood to perform anomaly detection with generative models; and why high-dimensional Gaussians are “soap bubbles”. This post is a summary of my current thoughts on the topic. First, some context: one of the reasons I’m writing this, is to structure my own thoughts about typicality and the unintuitive behaviour of high-dimensional probability distributions. Mos

Explore this link on the map →

saved by

related reading