Factorizable Normalizing Flows represent parameter-dependent densities via a reference flow composed with a factorized polynomial transformation, enabling isolated per-parameter learning and linear scaling.
Johnson, and Patrick M
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Customized chromatic noise models applied to NANOGrav 15 yr data raise the Bayes factor for Hellings-Downs GWB correlations by a factor of ~8, lower the amplitude to 2.1e-15, and increase the spectral index to 3.5.
citing papers explorer
-
Factorizable Normalizing Flows for parameter-dependent density morphing
Factorizable Normalizing Flows represent parameter-dependent densities via a reference flow composed with a factorized polynomial transformation, enabling isolated per-parameter learning and linear scaling.