I(X;Y) = H(X) + H(Y) - H(X,Y) = E[log p(X,Y)/p(X)p(Y)]. Symmetric. Channel-capacity = max I. Bridges info-theory + statistics + ML (variational lower bounds).
I(X;Y) = H(X) + H(Y) - H(X,Y) = E[log p(X,Y)/p(X)p(Y)]. Symmetric. Channel-capacity = max I. Bridges info-theory + statistics + ML (variational lower bounds).