On the Convergence of the <i>EM</i> Algorithm 论文
1983Journal of the Royal Statistical Society Series B (Statistical Methodology)引用 336
Control Systems and IdentificationBlind Source Separation TechniquesBayesian Methods and Mixture Models
摘要
SUMMARY An example is given showing that a sequence generated by a GEM algorthm need not converge under the conditions stated in Dempster et al., (1977). Two general convergence results are presented which suggest that in practice a GEM sequence will converge to a compact connected set of local maxima of the likelihood function; this limit set may or may not consist of a single point.