Feature informativeness, curse-of-dimensionality and error probability in discriminant analysis.
Tatjana Pavlenko · Lund University Publications (Lund University) · 2001
This thesis is based on four papers on high-dimensional discriminant analysis. Throughout, the curse-of-dimensionality effect on the precision of the discrimination performance is emphasized. A growing dimension asymptotic approach is used for assessing this effect and the limiting error probability are taken as the performance criteria. A combined effect of a high dimensionality and feature informativeness on the discrimination performance is evaluated.