Monotonically Decreasing Sequence of Divergences (1910.00402v3)

Abstract: Divergences are quantities that measure discrepancy between two probability distributions and play an important role in various fields such as statistics and machine learning. Divergences are non-negative and are equal to zero if and only if two distributions are the same. In addition, some important divergences such as the f-divergence have convexity, which we call "convex divergence". In this paper, we show new properties of the convex divergences by using integral and differential operators that we introduce. For the convex divergence, the result applied the integral or differential operator is also a divergence. In particular, the integral operator preserves convexity. Furthermore, the results applied the integral operator multiple times constitute a monotonically decreasing sequence of the convex divergences. We derive new sequences of the convex divergences that include the Kullback-Leibler divergence or the reverse Kullback-Leibler divergence from these properties.