Why it matters
Score matching underlies diffusion theory. Understanding shapes fundamentals.
Advertisement
The architecture
Nabla log p(x): score function.
Denoising score matching: perturb + predict noise.
Equivalent to diffusion training.
Advertisement
How it works end to end
Denoising score matching (DSM).
Score = -noise / sigma up to constant.
Yang Song's noise-conditional score networks (NCSN).