论文信息 - On Density Estimation under Relative Entropy Loss Criterion - 字舞流文

On Density Estimation under Relative Entropy Loss Criterion

A density estimation problem under relative entropy loss criterion is considered. When the densities estimated constitute a d-dimensional smooth parameter family, an exact asymptotics of the minimax risk is established.

Shun-ichi Amari | Marat V. Burnashev

[1] Grace L. Yang,et al. Asymptotics In Statistics , 1990 .

[2] Abraham Wald,et al. Statistical Decision Functions , 1951 .

[3] E. Lehmann. Testing Statistical Hypotheses , 1960 .

[4] Thomas M. Cover,et al. Elements of Information Theory , 2005 .

[5] T. N. Sriram. Asymptotics in Statistics–Some Basic Concepts , 2002 .

[6] Shun-ichi Amari,et al. Statistical Theory of Learning Curves under Entropic Loss Criterion , 1993, Neural Computation.

[7] B. V. Bahr,et al. Inequalities for the $r$th Absolute Moment of a Sum of Random Variables, $1 \leqq r \leqq 2$ , 1965 .

[8] Yuhong Yang,et al. Information-theoretic determination of minimax rates of convergence , 1999 .