Timeline for $H(p) \le H(q) + KL(p, q)$?
Current License: CC BY-SA 4.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 31, 2019 at 17:01 | vote | accept | Xi Wu | ||
| Dec 31, 2019 at 17:00 | comment | added | Xi Wu | @RémiPeyre: Replied with motivations on my side. | |
| Dec 31, 2019 at 17:00 | history | edited | Xi Wu | CC BY-SA 4.0 |
added 1139 characters in body
|
| Dec 30, 2019 at 18:25 | answer | added | Algernon | timeline score: 5 | |
| Dec 30, 2019 at 15:14 | comment | added | user111 | A similar question (with answer in continuous and discrete cases) appears here. | |
| Dec 30, 2019 at 15:14 | answer | added | Rémi Peyre | timeline score: 5 | |
| Dec 30, 2019 at 15:11 | comment | added | Rémi Peyre | Are you sure you want to write you inequality with $\mathit{KL}(p, q)$, not $\mathit{KL}(q, p)$? In information theory, $H(q) + \mathit{KL}(q, p)$ has a nice meaning (it is the cost to describe $q$ when using a description method optimized for $p$); while, as far as I know, $H(q) + \mathit{KL}(p, q)$ does not mean anything interesting… | |
| Dec 30, 2019 at 14:20 | answer | added | Steve | timeline score: 4 | |
| Dec 30, 2019 at 10:09 | history | asked | Xi Wu | CC BY-SA 4.0 |