Timeline for Is this generalization bound proof wrong?
Current License: CC BY-SA 3.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| May 2, 2017 at 3:42 | vote | accept | axk | ||
| Jul 31, 2018 at 20:25 | |||||
| May 2, 2017 at 3:32 | answer | added | Henry.L | timeline score: 2 | |
| May 2, 2017 at 3:10 | comment | added | Henry.L | Suppose the attainment of supremum occurs at $h_{0}\in\mathcal{H}$,$Pr\left[sup_{h\in\mathcal{H}}\left|\widehat{E}(h,S_{1})-\widehat{E}(h,S_{2})\right|>\frac{\epsilon}{2}\right]=Pr\left[\left|\widehat{E}(h_{0},S_{1})-\widehat{E}(h_{0},S_{2})\right|>\frac{\epsilon}{2}\right]\leq_{1-2\delta}Pr\left[\left|\widehat{E}(h_0',S'_{1})-\widehat{E}(h_0',S'_{2})\right|>\rho(h_{0})\right]\leq Pr\left[sup_{h'\in\mathcal{H}}\left|\widehat{E}(h',S'_{1})-\widehat{E}(h',S'_{2})\right|>\rho(h_{0})\right]$ is what they argued. | |
| May 2, 2017 at 2:40 | comment | added | axk | Lemma 3.5 is fine -- there h is fixed. It becomes problematic when it is applied in a context where the bound needs to be uniform over all $h$ in $\mathcal H$. | |
| May 2, 2017 at 2:37 | comment | added | Henry.L | Are you saying that their Lemma 3.5 is problematic? The step you mentioned is no more than a direct application of Lemma 3.5. | |
| May 2, 2017 at 2:10 | history | asked | axk | CC BY-SA 3.0 |