Skip to content
All tags

#diffusion-models

2 posts

Diffusion Models: Forward Noise, Reverse Generation, and the ELBO

Chapter 14 starts with a fixed Gaussian noising Markov chain and learns to reverse each transition. The ELBO turns reverse-kernel matching into weighted noise prediction, while the continuous-time view explains reverse drift through the score ∇log p_t.

Adversarial Robustness and Generative Models: It's Not Nonlinearity, It's Linearity

Researchers initially assumed neural networks are easy to fool because they're nonlinear. That was wrong — Goodfellow's 2014 paper argues the primary cause is their linear nature, and high dimensionality lets every tiny perturbation compound. The second half covers generative models: GANs' three pathologies, and why diffusion sidesteps two of them by adding noise and learning to remove it.