3. [18] Given two probability distributions p(x) and q(x), their KullbackLeibler distance is defined as DL(p, q)

Question:

3. [18] Given two probability distributions p(x) and q(x), their Kullback–Leibler distance is defined as DL(p, q) := E(p log p

q

). (2.3.105)

Prove that DL(p, q) ≥ 0. Suppose we define the symmetric function S(p, q) := DL(p, q) +

DL(q, p). Is this a metrics?

Fantastic news! We've Found the answer you've been seeking!

Step by Step Answer:

Question Posted: