A parametrization scheme for classifying models of learnability
Shai Ben-David, Gyora M. Benedek, Yishay Mansour · Conference on Learning Theory · 1989
We present a systematic framework for classifying, comparing and defining models of computational learnability. Apart from the obvious ‘uniformity’ parameters we present a novel ‘solid learnability’ notion that captures the difference between ‘Guess and Test’ learning algorithms and learnability notions for which consistency with the samples guarantees success.