Noise robustness and stochastic tolerance of OT error-driven ranking algorithms

Recent counterexamples show that Harmonic Grammar (HG) error-driven learning (with the classical Perceptron reweighing rule) is not robust to noise and does not tolerate the stochastic implementation (Magri 2014, MS). This article guarantees that no analogous counterexamples are possible for proper Optimality Theory (OT) error-driven learners. In fact, a simple extension of the OT convergence analysis developed in the literature (Tesar and Smolensky 1998, Linguist. Inq., 29, 229–268; Boersma 2009, Linguist. Inq., 40, 667–686; Magri 2012, Phonology, 29, 213–269) is shown to ensure stochastic tolerance and noise robustness of the OT learner. Implications for the comparison between the HG and OT implementations of constraint-based phonology are discussed.