Uohashi Keiko
Faculty of Engineering, Tohoku Gakuin University, Tagajo 985-8537, Miyagi, Japan.
Entropy (Basel). 2022 Nov 28;24(12):1736. doi: 10.3390/e24121736.
This study considers a new decomposition of an extended divergence on a foliation by deformed probability simplexes from the information geometry perspective. In particular, we treat the case where each deformed probability simplex corresponds to a set of -escort distributions. For the foliation, different -parameters and the corresponding α-parameters of dualistic structures are defined on each of the various leaves. We propose the divergence decomposition theorem that guides the proximity of -escort distributions with different -parameters and compare the new theorem to the previous theorem of the standard divergence on a Hessian manifold with a fixed α-parameter.
本研究从信息几何的角度考虑了一种基于变形概率单纯形的叶状结构上扩展散度的新分解。特别地,我们处理了每个变形概率单纯形对应一组 - 护送分布的情况。对于叶状结构,在各个不同的叶上定义了不同的 - 参数和对偶结构的相应α - 参数。我们提出了散度分解定理,该定理指导具有不同 - 参数的 - 护送分布之间的接近程度,并将新定理与具有固定α - 参数的黑塞流形上标准散度的先前定理进行比较。