Joint and Separate Convexity of the Bregman Distance

105 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Bregman strongly nonexpansive operators in reflexive Banach spaces (2013, background): “In this paper, we are concerned with certain analogous classes of operators which are, in some sense, strongly nonexpansive not with respect to the norm, but with respect to Bregman distances [3, 14, 18, 21].”
Composite Binary Losses (2009, background): “(1966) and Savage (1971) and recently studied in a machine learning context by Buja et al. (2005) and Masnadi-Shirazi and Vasconcelos (2009).”
Distributed Online Optimization in Dynamic Environments Using Mirror Descent (2016, background): “, [21] for more details on Bregman divergence).”
A Descent Lemma Beyond Lipschitz Gradient Continuity: First-Order Methods Revisited and Applications (2017, background): “In fact, as pointed out by Iusem, (see Bauschke and Borwein [3]), Dh is symmetric if and only if h is a nondegenerate convex quadratic form (with domh= d).”
Convex Functions: Constructions, Characterizations and Counterexamples (2010, background): “29 (Joint and separate convexity on R [34]).”