Do you have a distributional definition of this? Like for example a conditional distribution like P(W=w|P=p)?
I would appreciate if someone can help me to prove the following proposition.
Let and be arbitrary distributions over let denote the usual Euclidean norm. how we can prove that the Hellinger distance is the norm of vector with th coordinate equal to the difference of the square roots of the probabilities of seeing according to and
normalized by dividing by . that is prove
Thanks in advance.