TY - JOUR
T1 - Generalizing Skew Jensen Divergences and Bregman Divergences With Comparative Convexity
AU - Nielsen, Frank
AU - Nock, Richard
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/8
Y1 - 2017/8
N2 - Comparative convexity is a generalization of ordinary convexity based on abstract means instead of arithmetic means. We introduce the generalized skew Jensen divergences and their corresponding Bregman divergences with respect to comparative convexity. To illustrate those novel families of divergences, we consider the convexity induced by quasi-arithmetic means, and report explicit formula for the corresponding Bregman divergences. In particular, we show that those new Bregman divergences are equivalent to conformal ordinary Bregman divergences on monotone embeddings, and further state related results.
AB - Comparative convexity is a generalization of ordinary convexity based on abstract means instead of arithmetic means. We introduce the generalized skew Jensen divergences and their corresponding Bregman divergences with respect to comparative convexity. To illustrate those novel families of divergences, we consider the convexity induced by quasi-arithmetic means, and report explicit formula for the corresponding Bregman divergences. In particular, we show that those new Bregman divergences are equivalent to conformal ordinary Bregman divergences on monotone embeddings, and further state related results.
KW - Bregman divergence (BD)
KW - conformal divergence
KW - convexity
KW - quasi-arithmetic weighted mean
KW - regular mean
KW - skew Jensen divergence (JD)
UR - http://www.scopus.com/inward/record.url?scp=85028406148&partnerID=8YFLogxK
U2 - 10.1109/LSP.2017.2712195
DO - 10.1109/LSP.2017.2712195
M3 - Article
SN - 1070-9908
VL - 24
SP - 1123
EP - 1127
JO - IEEE Signal Processing Letters
JF - IEEE Signal Processing Letters
IS - 8
M1 - 7938742
ER -