Timeline for Concentration bound for a martingale-like setting (the expected difference decreases as the sequence increases)
Current License: CC BY-SA 3.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 10, 2015 at 19:52 | vote | accept | Daniel86 | ||
| Jan 10, 2015 at 19:52 | history | edited | Davide Giraudo | CC BY-SA 3.0 |
added 213 characters in body
|
| Jan 10, 2015 at 19:50 | comment | added | Davide Giraudo | The probability $P_2$ is equal to $0$ if $\alpha /2\geqslant \sum_{i=0}^{n-1} c_i$, so the bound is good for $\alpha$ large. | |
| Jan 10, 2015 at 19:11 | comment | added | Daniel86 | Thank you very much, @Davide, but I may be missing something here. Say $c_{i} = (i+1)^{-2}$. How is upper-bounding $P_{2}$ an easier task than the original question (note that in my original post, the term is $i\sqrt{Y_{i}}$)? | |
| Jan 10, 2015 at 12:55 | history | answered | Davide Giraudo | CC BY-SA 3.0 |