Generalized gamma scale mixtures of normals fit coefficients from Fourier, wavelet, and CNN transformations of large image datasets substantially better than standard priors like Gaussian, Laplace, or Student's t.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.AP 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Do Generalized-Gamma Scale Mixtures of Normals Fit Large Image Datasets?
Generalized gamma scale mixtures of normals fit coefficients from Fourier, wavelet, and CNN transformations of large image datasets substantially better than standard priors like Gaussian, Laplace, or Student's t.