The α-EM algorithm and its applications

Author

Matsuyama, Yasuo

Author_Institution

Dept. of Electr., Electron. & Comput. Eng., Waseda Univ., Tokyo, Japan

Volume

1

fYear

2000

fDate

2000

Firstpage

592

Abstract

The α-EM algorithm is a super-class of the traditional expectation-maximization (EM) algorithm. This algorithm is derived by computing the likelihood ratio of incomplete data through an extended logarithm; namely, the α-logarithm. The case of α=-1 corresponds to the logarithm. The number α adjusts eigenvalues of update matrices by reflecting the optimization function´s second-order properties with respect to the estimation parameter. This property shows merits on speedup of convergence. In the paper, a derivation of the algorithm is given first. Then, convergence and speedup properties are discussed. Finally, the applicability of the α-FM algorithm and examples are shown

Keywords

Hessian matrices; Jacobian matrices; convergence of numerical methods; eigenvalues and eigenfunctions; iterative methods; maximum likelihood estimation; optimisation; parameter estimation; α-EM algorithm; α-logarithm; convergence speed; eigenvalues; estimation parameter; expectation-maximization algorithm; extended logarithm; incomplete data likelihood ratio; iterative optimization; optimization function; update matrices; Convergence; Cost function;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on

Conference_Location

Istanbul

ISSN

1520-6149

Print_ISBN

0-7803-6293-4

Type

conf

DOI

10.1109/ICASSP.2000.862051

Filename

862051