Extends minimum-distance estimators to Hellinger distance via reverse data processing inequalities, yielding the first near-linear time algorithms for univariate mixtures of log-concave densities and Gaussians with near-optimal sample complexity.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Density estimation for Hellinger via minimum-distance estimators: mixtures of Gaussians, log-concave, and more
Extends minimum-distance estimators to Hellinger distance via reverse data processing inequalities, yielding the first near-linear time algorithms for univariate mixtures of log-concave densities and Gaussians with near-optimal sample complexity.