Return to Revisions

2 of 4

I add a tag.

edit approved Jul 29, 2018 at 0:03

Is KL divergence $D(P||Q)$ strongly convex over $P$ in infinite dimension

By KL divergence I mean $D(P||Q) = \int dP \log(\frac{dP}{dQ})$. I am looking for the conditions under which this strong convexity is true and possible references. I could not find an answer for infinite dimensions.

it.information-theory convex-analysis

asked Jul 28, 2018 at 21:47

Maziar Sanjabi