2000 character limit reached
A Formal Proof of PAC Learnability for Decision Stumps (1911.00385v3)
Published 1 Nov 2019 in cs.LG, cs.LO, and stat.ML
Abstract: We present a formal proof in Lean of probably approximately correct (PAC) learnability of the concept class of decision stumps. This classic result in machine learning theory derives a bound on error probabilities for a simple type of classifier. Though such a proof appears simple on paper, analytic and measure-theoretic subtleties arise when carrying it out fully formally. Our proof is structured so as to separate reasoning about deterministic properties of a learning function from proofs of measurability and analysis of probabilities.