A data-compression technique reduces NPMLE computation cost to logarithmic in n for exponential family mixtures, while approximate NPMLEs attain near-parametric rates for marginal density estimation.
For eachx∈R, the likelihood kernell θ(x)is unimodal inθ, with unique mode atµ −1(x)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fast computation and theoretical guarantees for the NPMLE in exponential family mixtures
A data-compression technique reduces NPMLE computation cost to logarithmic in n for exponential family mixtures, while approximate NPMLEs attain near-parametric rates for marginal density estimation.