Maximum smoothed likelihood density estimation for inverse problems

DOI10.1214/aos/1176324463zbMath0822.62025OpenAlexW1968608259MaRDI QIDQ1895354

Paul P. B. Eggermont, Vincent N. La Riccia

Publication date: 10 September 1995

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aos/1176324463

zbMATH Keywords

stabilityconvergenceregularizationstrong law of large numbersEM algorithmlaw of the iterated logarithmalmost sure convergenceintegral equation of the first kindkernel density estimatorscompact integral operatorlarge sample asymptotic problemmaximum smoothed likelihood density estimationmaximum smoothed likelihood formalismnonlinearly smoothed algorithmstrong convergence properties

Mathematics Subject Classification ID

Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20) Numerical methods for ill-posed problems for integral equations (65R30)

Related Items

Convergence of an iterative algorithm to the nonparametric MLE of a mixing distribution ⋮ A note on density estimation for Poisson mixtures ⋮ Universal smoothing factor selection in density estimation: theory and practice. (With discussion) ⋮ Linear inverse problems for Markov processes and their regularisation ⋮ Revisiting consistency of a recursive estimator of mixing distributions ⋮ Maximum penalized likelihood estimation and smoothed em algorithms for positive integral equatioins of the first kind ⋮ N-stage splitting for maximum penalized likelihood estimation ⋮ EM Algorithms ⋮ EM Algorithms from a Non-stochastic Perspective ⋮ A survey of nonparametric mixing density estimation via the predictive recursion algorithm ⋮ Log-density estimation in linear inverse problems ⋮ Maximum smoothed likelihood component density estimation in mixture models with known mixing proportions ⋮ Estimating a mixing distribution on the sphere using predictive recursion ⋮ Maximum likelihood estimation of smooth monotone and unimodal densities.