WRSWorld Research StateContribute
WORLD RESEARCH STATE

Schapire: the strength of weak learnability

Contribution grade

Statistical learning · THEOREM

Reference score260,000Provisional editorial estimate of this exact contribution; its grade is assessed separately.

What changed

Proved weak/strong PAC learnability equivalence and constructed an accuracy-amplifying learner under the paper's assumptions.

Scientific scope

The record is Schapire's sole-author 1990 Machine Learning article. The theorem uses the paper's PAC assumptions; it does not absorb Kearns and Valiant's prior formulation, Freund–Schapire AdaBoost or later practical boosting analyses.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is Schapire's sole-author 1990 Machine Learning article. The theorem uses the paper's PAC assumptions; it does not absorb Kearns and Valiant's prior formulation, Freund–Schapire AdaBoost or later practical boosting analyses.

Contributors

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction