Timeline for Best possible concentration inequality in high dimensions
Current License: CC BY-SA 3.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 20, 2017 at 18:52 | comment | added | TOM | I indeed meant that the Euclidean distance. | |
| Nov 14, 2014 at 3:23 | comment | added | Mark Meckes | Ah, or by $\|X_i\|_2 \le 1$ did you mean that the Euclidean norm of $X_i$ is almost surely at most 1? I thought you were referring to the $L^2$ norm of a random variable. In that case, you can e.g. use a vector-valued version of Talagrand's inequality to get the same type of result as the one dimensional case. | |
| Nov 14, 2014 at 1:25 | comment | added | Mark Meckes | Yes, in 1 dimension this is Hoeffding's inequality if you have boundedness, but that was never mentioned. | |
| Nov 13, 2014 at 20:18 | comment | added | TOM | In 1 dimension this is exaclty hoeffding's inequality, unless I missed something obvious (we have boundedness, zero mean and independence). | |
| Nov 12, 2014 at 3:42 | comment | added | Mark Meckes | You need additional assumptions, even in the one-dimensional case, for Hoeffding's inequality to hold. | |
| Nov 10, 2014 at 22:33 | history | edited | TOM | CC BY-SA 3.0 |
added 252 characters in body
|
| Nov 10, 2014 at 17:23 | history | asked | TOM | CC BY-SA 3.0 |