5,322
edits
Machine Learning: Difference between revisions
→Theory
(→Theory) |
|||
| Line 221: | Line 221: | ||
====Theory==== | ====Theory==== | ||
[https://nowak.ece.wisc.edu/SLT09/lecture8.pdf Reference]<br> | [https://nowak.ece.wisc.edu/SLT09/lecture8.pdf Reference]<br> | ||
In the case where the Hypothesis class <math>\mathcal{H}</math> is finite, we have | In the case where the Hypothesis class <math>\mathcal{H}</math> is finite, we have with probability <math>1-\delta</math> | ||
* <math>|L_D(h) - L_S(h)| < \sqrt{ | * <math>|L_D(h) - L_S(h)| < \sqrt{ | ||
\frac{\log|\mathcal{H}| + \log(1/\delta)}{2m}} | \frac{\log|\mathcal{H}| + \log(1/\delta)}{2m}} | ||