Weak learner ($ϵ\le 1/2-\gamma$)

For weighted binary data, a weak learner supplies a classifier whose weighted error is below one half. A uniform edge $\gamma >0$ for every weighting permits a quantitative AdaBoost training error bound. This training-weight condition is a separate assumption from merely having error below one half on the initial unweighted sample.

// Target: foundations-of-mathematics.bigb