Asymptotically optimal function estimation by minimum complexity criteria
暂无分享,去创建一个
The minimum description length principle applied to function estimation can yield a criterion of the form log(likelihood)+const/spl middot/m instead of the familiar log(likelihood)+(m/2) log n where m is the number of parameters and n is the sample size. The improved criterion yields minimax optimal rates for redundancy and statistical risk. The analysis suggests an information-theoretic reconciliation of criteria proposed by Rissanen (1983), Schwarz (1978), and Akaike (1973).<<ETX>>
[1] H. Akaike,et al. Information Theory and an Extension of the Maximum Likelihood Principle , 1973 .
[2] G. Schwarz. Estimating the Dimension of a Model , 1978 .
[3] Jorma Rissanen,et al. Universal coding, information, prediction, and estimation , 1984, IEEE Trans. Inf. Theory.
[4] Andrew R. Barron,et al. Minimum complexity density estimation , 1991, IEEE Trans. Inf. Theory.
[5] Jorma Rissanen,et al. Density estimation by stochastic complexity , 1992, IEEE Trans. Inf. Theory.