Concept
Denoising score matching
Denoising score matching is a training objective for learning the score function of a data distribution, where the score is the gradient of the log-density with respect to the input, ∇_x log p(x). Directly estimating this score is hard because you never observe the true…
The rest of “Denoising score matching” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→