Symmetrizing Bregman Divergence on the Cone of Positive Definite Matrices: Which Mean to Use and Why

View PDF HTML (experimental)

Abstract:This work uncovers variational principles behind symmetrizing the Bregman divergences induced by generic mirror maps over the cone of positive definite matrices. We show that computing the canonical means for this symmetrization can be posed as minimizing the desired symmetrized divergences over a set of mean functionals defined axiomatically to satisfy certain properties. For the forward symmetrization, we prove that the arithmetic mean over the primal space is canonical for any mirror map over the positive definite cone. For the reverse symmetrization, we show that the canonical mean is the arithmetic mean over the dual space, pulled back to the primal space. Applying this result to three common mirror maps used in practice, we show that the canonical means for reverse symmetrization, in those cases, turn out to be the arithmetic, log-Euclidean and harmonic means. Our results improve understanding of existing symmetrization practices in the literature, and can be seen as a navigational chart to help decide which mean to use when.

Subjects:

Optimization and Control (math.OC); Machine Learning (cs.LG); Systems and Control (eess.SY); Machine Learning (stat.ML)

Cite as: arXiv:2603.28917 [math.OC]

(or arXiv:2603.28917v1 [math.OC] for this version)

https://doi.org/10.48550/arXiv.2603.28917

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Abhishek Halder [view email] [v1] Mon, 30 Mar 2026 18:48:50 UTC (77 KB)