Convexity of mutual information along the heat flow
Andre Wibisono, Varun Jog

TL;DR
This paper investigates the convexity properties of mutual information during the heat flow evolution, establishing conditions for convexity and providing counterexamples for nonconvexity at small times.
Contribution
It proves mutual information is convex along heat flow for log-concave initial distributions and eventually convex for broader classes, with counterexamples at small times.
Findings
Mutual information is convex over time for log-concave initial distributions.
Mutual information becomes convex at large times for distributions with finite moments and Fisher information.
Counterexamples show mutual information can be nonconvex at small times.
Abstract
We study the convexity of mutual information along the evolution of the heat equation. We prove that if the initial distribution is log-concave, then mutual information is always a convex function of time. We also prove that if the initial distribution is either bounded, or has finite fourth moment and Fisher information, then mutual information is eventually convex, i.e., convex for all large time. Finally, we provide counterexamples to show that mutual information can be nonconvex at small time.
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.
