散度分解为三个散度的和分解
Sum decomposition of divergence into three divergences
摘要：
在机器学习、统计学和信号处理等领域中，发散函数作为度量两点之间差异的重要工具。著名的发散是Bregman发散、Jensen发散和f-发散。本文证明了对称Bregman发散可以分解为两类Jensen发散和Bregman发散。此外，应用这个结果，我们证明了另一个和分解的分歧是可能的，其中包括明确的f-分歧。
英文摘要：
Divergence functions play a key role as to measure the discrepancy between two points in the field of machine learning, statistics and signal processing. Well-known divergences are the Bregman divergences, the Jensen divergences and the f-divergences. In this paper, we show that the symmetric Bregman divergence can be decomposed into the sum of two types of Jensen divergences and the Bregman divergence. Furthermore, applying this result, we show another sum decomposition of divergence is possible which includes f-divergences explicitly.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
