A spectral framework converts KL divergence estimation into least-squares problems and yields closed-form estimators for relative log-densities and divergences from feature moments.
Information theory with kernel methods.IEEE Transactions on Information Theory, 69(2):752–775, 2023.(cited on pages 3, 4, 6, 7, 9, 13, 19, 22, 29, and 36)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
A Spectral Framework for Closed-Form Relative Density Estimation
A spectral framework converts KL divergence estimation into least-squares problems and yields closed-form estimators for relative log-densities and divergences from feature moments.