On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes
authors: Andrew Ng, Michael Jordan year: 2001 See in Zotero
Literature Notes
Compares generative and discriminative models, by computing classification using both and compares the model error and convergence of each.
Most of the time people prefer discriminative. A lot of times the asymptotic error for a generative model is higher. However, generative models can converge to the asymptotic error faster, so given little data the generative model might be better.