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.

$\endgroup$

1 Answer 1

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 and acknowledge that you have read and understand our privacy policy and code of conduct.

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