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

Matt Franklin: In the proof of Theorem 8.66 (middle of p. 225 in book), the...Matt Franklin: The "Condorcet Jury Theorem" is discussed but not named in t...Matt Franklin: In the first line of the proof of Proposition 8.45 (bottom o...Ryan O'Donnell: Great catch, thanks!Ryan O'Donnell: Thanks! The proofreader should have caught those!Ryan O'Donnell: Thanks -- I think that kind of parenthesis-free notation for...Ryan O'Donnell: Thanks! Unique Games is discussed somewhat in Chapter 7 of ...