Computational learning theory is an area of algorithms research devoted to the following task: given a source of “examples” $(x, f(x))$ from an unknown function $f$, compute a “hypothesis” function $h$ which is good at predicting $f(y)$ on future inputs $y$. We will focus on just one possible formulation of the task:

[...]

## Recent comments

Ohad Klein: In lemma 46 (48) - should it be $i \not \in J'_x$? (In its ...Ohad Klein: Another one - is the symbol "union" is redundant in 37b,c?Ohad Klein: I might be misunderstanding 37b. Suppose k=n=1. Then $E[f^q]...Ohad Klein: I might be wrong, but in ex. 9.31 (i.e. remark 9.29), I trie...Ohad Klein: sorry, my bad, again!Ohad Klein: In 23, is it $q \leq 2+2\epsilon$?Ohad Klein: ctrl+f: Paresval.