The Teaching Dimension of Linear Learners


Ji Liu, Xiaojin Zhu, Hrag Ohannessian ;
Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:117-126, 2016.


Teaching dimension is a learning theoretic quantity that specifies the minimum training set size to teach a target model to a learner. Previous studies on teaching dimension focused on version-space learners which maintain all hypotheses consistent with the training data, and cannot be applied to modern machine learners which select a specific hypothesis via optimization. This paper presents the first known teaching dimension for ridge regression, support vector machines, and logistic regression. We also exhibit optimal training sets that match these teaching dimensions. Our approach generalizes to other linear learners.

Related Material