Characterizing the Functional Density Power Divergence Class

Divergence measures have a long association with statistical inference, machine learning and information theory. The density power divergence related produced many useful (and popular) procedures, which provide good balance between model efficiency on one hand outlier stability or robustness the other. logarithmic divergence, particular transform of has also been very successful in producing efficient stable inference procedures; addition it led to significant demonstrated applications success minimum procedures based (which go by names $\beta $ -divergence notation="LaTeX">$\gamma -divergence, respectively) make imperative meaningful look for other, similar divergences may be obtained as transforms same spirit. With this motivation we search such referred herein functional class. present article characterizes class, thus identifies available within construct that explored further possible