Optimization of Barron density estimates

IEEE Transactions on Information Theory

Volumn 47, Issue 5, 2001, Pages 1867-1883

  Vajda, Igor ^b   Van der Meulen, Edward C ^c  

^a UNIVERSITY OF LEUVEN   (Belgium)

^b INSTITUTE OF INFORMATION THEORY AND AUTOMATION   (Czech Republic)

^c NONE

Author keywords

Barron estimator; Chi square criterion; Consistency; Density estimation; Exponential family; Information divergence criterion; Optimization; Rate of consistency

Indexed keywords

COMPUTER SIMULATION; MAXIMUM LIKELIHOOD ESTIMATION; OPTIMIZATION; PROBABILITY DENSITY FUNCTION;

BARRON ESTIMATORS; CHI-SQUARE DIVERGENCE;

CODING ERRORS;

EID: 0035397258     PISSN: 00189448     EISSN: None     Source Type: Journal    
DOI: 10.1109/18.930924     Document Type: Article

References (29)

1. Uniformly powerful goodness of fit tests
2. The convergence in information of probability density estimators
3. Distribution estimation consistent in total variation and in two types of information divergence
4. 2-errors in histogram density estimation
5. About the asymptotic accuracy of Barron density estimates
6. Asymptotic normality of relative entropy in multivariate density estimation
7. On some global measures of the deviations of density function estimates
8. Eine informationstheoretische ungleichung und ihre Anwendung auf den Beweis der Ergodizität von Markoffschen Ketten
9. No empirical measure can converge in total variation sense for all distributions
10. 2 -divergence
11. On Kullback-Leibler loss and density estimation
12. Optimal partitions and dominating distributions for Barron density estimates
13. About the chi-square error of Barron density estimate
14. The chi-square error of Barron estimator of regular density is asymptotically normal