Timeline for concentration inequality for $d$-dimensional martingale
Current License: CC BY-SA 4.0
8 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
Jun 28, 2021 at 17:00 | comment | added | Iosif Pinelis | @FinnLim : Oftentimes, the bounds on moments $E|X|^p$ are only available for large enough $p$. That is why I had this provision, $p>p_0$ | |
Jun 28, 2021 at 16:57 | history | edited | Iosif Pinelis | CC BY-SA 4.0 |
added 2 characters in body
|
Jun 28, 2021 at 16:27 | comment | added | Uzu Lim | Thank you for this. Is that a typo - does one replace $p_0$ in the infimum by just $0$ (which I believe then simply follows from Markov's inequality)? | |
Dec 1, 2015 at 20:07 | comment | added | Iosif Pinelis | I have expanded the remark about deriving bounds on tails from bounds on moments. Also, what is sometimes referred to as the Azuma inequality is in fact due entirely to Hoeffding (1963, Journal of the American Statistical Association) -- see Theorem 2 and the last paragraph of Section 2 therein. | |
Dec 1, 2015 at 20:06 | history | edited | Iosif Pinelis | CC BY-SA 3.0 |
I have expanded the remark about deriving bounds on tails from bounds on moments.
|
Dec 1, 2015 at 5:13 | comment | added | Sosha | @losif: Thanks. I'll check. Actually, I want a Azuma kind of inequality. | |
Dec 1, 2015 at 5:12 | vote | accept | Sosha | ||
Nov 30, 2015 at 16:22 | history | answered | Iosif Pinelis | CC BY-SA 3.0 |