A note on the approximate symmetry of Bregman distances

Abstract

The Bregman distance B_x(y,x), x ∈ ∂ J(y), associated to a convex sub-differentiable functional J is known to be in general non-symmetric in its arguments x, y. In this note we address the question when Bregman distances can be bounded against each other when the arguments are switched, i.e., if some constant C>0 exists such that for all x,y on a convex set M it holds that 1C B_x(y,x) ≤ B_y(x,y) ≤ C B_x(y,x). We state sufficient conditions for such an inequality and prove in particular that it holds for the p-powers of the p and Lp-norms when 1 < p <∞.

0

Turn this paper into a lesson

ArcXiv compiles a structured reading guide from this paper's metadata: plain-English importance, contributions, prerequisite concepts, which sections to read first, flashcards, and a quiz. Grounded in the abstract, never invented.

Discussion (0)

Sign in to join the discussion.

Loading comments…