← 研踪 PaperTrailarXiv:2607.24197 · v6
Bregman Power Divergences
首次提交 2026-07-27 17:18
版本更新 2026-11-19 13:59
雷达观测 2026-11-20 19:58
摘要
Power distances between weighted Euclidean points are fundamental dissimilarity measures in computational geometry, used notably for constructing power diagrams and their dual weighted regular triangulations. Bregman divergences, on the other hand, are fundamental deviation measures in information theory and serve as canonical divergences of dually flat spaces in information geometry. In this work, we introduce Bregman power divergences, an extension of power distances to Bregman divergences, and provide two complementary geometric interpretations of that measure based on (i) the Bregman potential lifting and on (ii) the Bregman Pythagorean theorem. We show that Bregman power divergences between weighted parameters amount to equivalent ordinary power distances expressed using the mixed-parameterization induced by the convex duality of Bregman generators. This equivalence enables Bregman proximity problems to be solved as Euclidean proximity tasks at the expense of using an extra dimension. As an illustration of this equivalence, we reduce the Bregman diameter and closest-pair problems to Euclidean power distance problems. In the second part, we further elucidate the correspondence between Bregman power divergences and power distances through the equivalence of Bregman potential lifting and paraboloid lifting techniques. Last, we consider the space of Bregman and power spheres, and show how to construct a Bregman circumsphere passing through prescribed parameters as a corresponding power circumsphere, called an orthosphere. We further discuss several applications.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v6 · 2026-11-19 13:59 · 最新观测版本
Bregman Power Divergences
Power distances between weighted Euclidean points are fundamental dissimilarity measures in computational geometry, used notably for constructing power diagrams and their dual weighted regular triangulations. Bregman divergences, on the other hand, are fundamental deviation measures in information theory and serve as canonical divergences of dually flat spaces in information geometry. In this work, we introduce Bregman power divergences, an extension of power distances to Bregman divergences, and provide two complementary geometric interpretations of that measure based on (i) the Bregman potential lifting and on (ii) the Bregman Pythagorean theorem. We show that Bregman power divergences between weighted parameters amount to equivalent ordinary power distances expressed using the mixed-parameterization induced by the convex duality of Bregman generators. This equivalence enables Bregman proximity problems to be solved as Euclidean proximity tasks at the expense of using an extra dimension. As an illustration of this equivalence, we reduce the Bregman diameter and closest-pair problems to Euclidean power distance problems. In the second part, we further elucidate the correspondence between Bregman power divergences and power distances through the equivalence of Bregman potential lifting and paraboloid lifting techniques. Last, we consider the space of Bregman and power spheres, and show how to construct a Bregman circumsphere passing through prescribed parameters as a corresponding power circumsphere, called an orthosphere. We further discuss several applications.
查看此版本解读 →查看此版本原文 ↗