Timeline for Set of distributions that minimize KL divergence,
Current License: CC BY-SA 3.0
5 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
Nov 12, 2013 at 4:49 | vote | accept | Raskol | ||
Nov 5, 2013 at 16:40 | answer | added | Arthur B | timeline score: 0 | |
Nov 5, 2013 at 15:44 | comment | added | Arthur B | Doesn't it make more sense to look at $\{q | D_{KL}(p||q) \leq \epsilon \}$? This would be a set of distributions that approximate $p$ well whereas you're looking at a set for which $q$ is a good approximation. | |
Nov 5, 2013 at 5:04 | comment | added | Ashok | In what context do you come across this? If it arises in problems like minimising $\mathbb{E}_p[X]$ subject to $p\in \mathcal{P}_{q,\epsilon}$, there is some duality which would help solving the problem. | |
Nov 4, 2013 at 12:12 | history | asked | Raskol | CC BY-SA 3.0 |