On the exact relationship between the denoising function and the data distribution
classification
💻 cs.NE
cs.LGstat.ML
keywords
datadenoisingrelationshipdistributionexactfunctionnoiseadditive
pith:BHDBDOFQ Add to your LaTeX paper
What is a Pith Number?\usepackage{pith}
\pithnumber{BHDBDOFQ}
Prints a linked pith:BHDBDOFQ badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more
read the original abstract
We prove an exact relationship between the optimal denoising function and the data distribution in the case of additive Gaussian noise, showing that denoising implicitly models the structure of data allowing it to be exploited in the unsupervised learning of representations. This result generalizes a known relationship [2], which is valid only in the limit of small corruption noise.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.