No-free-lunch theorem for machine learning

This entry is a formalization of the no-free-lunch theorem for machine learning following Section 5.1 of the book Understanding Machine Learning: From Theory to Algorithms by Shai Shalev-Shwartz and Shai Ben-David. The theorem states that for binary classification prediction tasks, there is no universal learner, meaning that for every learning algorithms, there exists a distribution on which it fails.