Entropy, Cross-Entropy, KL-Divergence


Entropy (at Information theory)

  • The expectation of bits that used for notating (or classify each other) probabilistic events when using optimal bits coding scheme. ( bits for notating events)
  • Entropy also can be interpreted as the average rate at which information is produced by stochastic source of data. (rare events have more information than an often occurring event.)
  • Entropy can be calculated by where is probability distribution. (Shannon’s source coding theorem)

Let’s think about the situation that you need to notate characters “A, B, C, D” in bits that stochastically written in a sentence. You can simply notate each character with 2 bits. For example, “00” for A, “01” for B, “10” for C, “11” for D. If every character have the same probability, () this notating is optimal notating. You used 2 bits for each character on average. (2 * 1/4 * 4)

But how about ? If you use same scheme, you will use 2 bits for each character on average. (2 * 1/2 + 2 * 1/4 + 2 * 1/8 * 2 = 2 * (1/2 + 1/4 + 1/8 + 1/8)) However, this is not optimal scheme for notating 4 character. As character A is frequently used than others, if you notate A with less bits, you can use less bits on average. So when notating “1” for A, “01” for B, “000” for C, “001” for D, 1.75 bits are used on average (1 * 1/2 + 2 * 1/4 + 3 * 1/8 * 2 = 1.75). In that case, you can decode bits by following rules:

  1. If looking bit is 1 or length of group of bits is 3, finish one character decoding.
  2. If looking bit is 0, add looking bit (0) to group of bits and looking next bit.

Cross-Entropy and KL-Divergence

The cross-entropy of the distribution relative to distribution over a given set is defined as follows:

You can think cross-entropy as applying coding scheme which is optimal to probability distribution () to probability distribution where is length of bits to coding i-th.

Kullback–Leibler divergence (KL-Divergence) can be thought of as something like a measurement of how far the distribution is from the distribution .

In deep learning, is dataset and is neural network output. Making cross-entropy loss smaller is making KL-Divergence of and ( ) smaller because is fixed value.