Timeline for Finite-sample deviation bound of empirical distribution from true distribution
Current License: CC BY-SA 4.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| May 21, 2019 at 8:55 | comment | added | dohmatob | Don't worry, I managed to lay my hands on a copy of ref [1]. Cheers! | |
| May 21, 2019 at 7:54 | comment | added | dohmatob | OK, great. Email sent. Thanks! | |
| May 21, 2019 at 7:47 | comment | added | Yuval Peres | Pinelis' paper covers $L^p$ for $p \ge 2$ provided $p$ is finite. I can send you the proof if you write to me at [email protected] Note the inequality definitely fails for $p=\infty$ where you need the $k$-dependence. | |
| May 21, 2019 at 5:59 | comment | added | dohmatob | Hum, it seems this result would hold for countably supported (not just finitely supported) $P$. Also, unfortunately, I don't have access to ref [1]. I was wondering whether the ideas presented there can be used to bound a general $L_p$-norm (where $1 \le p \le \infty$, and my original problem corresponds to the case $p=2$) of $\hat{P}_n-P$ ? | |
| May 20, 2019 at 17:54 | comment | added | dohmatob | Answer accepted. | |
| May 20, 2019 at 17:53 | vote | accept | dohmatob | ||
| May 20, 2019 at 17:46 | comment | added | Yuval Peres | Can you accept the answer? | |
| May 20, 2019 at 17:09 | comment | added | dohmatob | Nice. Also reference 1 is really nice. Thanks | |
| May 20, 2019 at 8:52 | history | answered | Yuval Peres | CC BY-SA 4.0 |