Review Note

Last Update: 10/08/2023 02:57 PM

Current Deck: EEN100: Theory and exercises

New Card (Unpublished)

Currently Published Content


Front
Back

No published tags.

Pending Suggestions


Field Change Suggestions:
Representative training set and ERM correctness
Assume that the training set \(\mathcal S\) is \(\epsilon/2\) representative.
Then (every) ERM prediction rule \(h_{\mathcal S} \in \arg\min_{h \in \mathcal H} L_{\mathcal S}(h)\) satisfies
\[L_{P_{\mathcal Z}}(h_{\mathcal S}) \le \min_{h' \in \mathcal H} L_{P_{\mathcal Z}}(h') + \epsilon\]i.e. is approximately correct.