Is there an interpretation of KL divergence which works for subjective probability (credence functions) where there is no concept of “true” or “false” distribution? And even for an objective interpretation, the term “cost” seems to be external to probability theory.
Is there an interpretation of KL divergence which works for subjective probability (credence functions) where there is no concept of “true” or “false” distribution? And even for an objective interpretation, the term “cost” seems to be external to probability theory.