Timeline for Concentration inequality for a function whose parameter depends on input samples
Current License: CC BY-SA 4.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 7, 2020 at 19:37 | vote | accept | Arnab | ||
| Dec 7, 2020 at 19:37 | comment | added | Arnab | Ah! ... Yes, of course. That should have been obvious. :( | |
| Dec 6, 2020 at 18:12 | comment | added | Yuval Peres | No, since in your formulation $\theta$ is a function of $X$, the average $$\frac{1}{n}\sum_i f_{\theta(X) }(X_i)$$ is also a function of $X$. | |
| Dec 4, 2020 at 22:10 | comment | added | Arnab | Thanks much. But viewing $f_\theta(x)$ as $f(x, \theta)$ and then to be able to apply Mcdiarmid, don't I need $\theta$ and $x$ to be independent? | |
| Dec 4, 2020 at 17:56 | history | answered | Yuval Peres | CC BY-SA 4.0 |