
TL;DR
This paper introduces a subclass of $f$-divergences called strongly convex divergences, establishing new relationships among them based on convexity properties.
Contribution
It defines strongly convex ($$-convex) $f$-divergences and derives novel and existing relationships among these divergences using convexity arguments.
Findings
New class of strongly convex divergences introduced
Relationships between $f$-divergences established using convexity
Theoretical framework for analyzing divergence properties
Abstract
We consider a sub-class of the -divergences satisfying a stronger convexity property, which we refer to as strongly convex, or -convex divergences. We derive new and old relationships, based on convexity arguments, between popular -divergences.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
