Timeline for McDiarmid-like inequality for subgassian random variables
Current License: CC BY-SA 3.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 18, 2019 at 21:01 | comment | added | Aryeh Kontorovich | $f$ is 1-Lipschitz under what metric? I don't think you actually need $X_n$ to be subgaussian. On the other hand, if they aren't independent, you'll definitely need some control over how strongly dependent they are (see mixing conditions). | |
| Oct 7, 2015 at 20:16 | history | edited | gappy3000 | CC BY-SA 3.0 |
added 26 characters in body
|
| Oct 7, 2015 at 17:51 | history | edited | gappy3000 | CC BY-SA 3.0 |
deleted 27 characters in body
|
| Oct 7, 2015 at 16:29 | history | asked | gappy3000 | CC BY-SA 3.0 |