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

Ryan O'Donnell: Good catch, thank you Xi.Ryan O'Donnell: Thank you! Sorry for the delay in replying.Ryan O'Donnell: Hi Ming. Here S stands for a fixed (non-random) subset of [...Xi Wu: typo: "our definition of $\mathbf{Inf}_i[f]$ from Chapter 2....Chengyu: Ex 2.c It should be "Suppose ... is an LTF with $\textbf{E}...Ming: I confuse the notation S in Fact 1.7. I wonder that the sym...Ryan O'Donnell: Yes, thanks! Sorry for the delay in replying.