0
$\begingroup$

Consider a hypothesis class $H = \cup_{n=1}^{\infty} H_n$, where for every $n\in N$, $H_n$ is finite. Find a weighting function $w : H ->[0, 1]$ such that $\sum_{h \in H} w(h) ≤ 1$ and so that for all $h \in H$, $w(h)$ is determined by $n(h) = min\{n :h \in H_n\} $ and by $|H_n(h)|$.
Since every $H_n$ is finite, it is agnostic PAC learnable. And hence their union $H$ is non-uniform learnable. However I am unable to proceed from here.

$\endgroup$
0
$\begingroup$

For every $n\in \mathbb{N}$, and $h\in H_n$, we can use $w(h)$ = $\frac{2^{−n}}{|H_n|} $.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.