If you've studied neural networks, then most of the applications you've come across were likely implemented using discriminative models. Generative adversarial networks, on the other hand, are part of a different class of models known as generative models. Discriminative models are those used for most supervised classification or regression problems. As an example of a classification problem, suppose you'd like to train a model to classify images of handwritten digits from 0 to 9. For that, you could use a labeled dataset containing images of handwritten digits and their associated labels indicating which digit each image represents. During the training process, you'd use an algorithm to adjust the model's parameters.

Yogatama, Dani, Dyer, Chris, Ling, Wang, Blunsom, Phil

We empirically characterize the performance of discriminative and generative LSTM models for text classification. We find that although RNN-based generative models are more powerful than their bag-of-words ancestors (e.g., they account for conditional dependencies across words in a document), they have higher asymptotic error rates than discriminatively trained RNN models. However we also find that generative models approach their asymptotic error rate more rapidly than their discriminative counterparts---the same pattern that Ng & Jordan (2001) proved holds for linear classification models that make more naive conditional independence assumptions. Building on this finding, we hypothesize that RNN-based generative classification models will be more robust to shifts in the data distribution. This hypothesis is confirmed in a series of experiments in zero-shot and continual learning settings that show that generative models substantially outperform discriminative models.

Agarwal, Arvind (University of Utah) | III, Hal Daume (University of Utah)

We present an approach to semi-supervised learning based on an exponential family characterization. Our approach generalizes previous work on coupled priors for hybrid generative/discriminative models. Our model is more flexible and natural than previous approaches. Experimental results on several data sets show that our approach also performs better in practice.

In this article, we will look at the difference between generative and discriminative models, how they contrast, and one another. Discriminative machine learning is to recognize the rig output among possible output choices. Given something about the data, and done by learning parameters. Classification is additionally mentioned as discriminative modeling. This is often on the grounds; the model must separate instances of input variables across classes.

Azeraf, Elie, Monfrini, Emmanuel, Pieczynski, Wojciech

We deal with Bayesian generative and discriminative classifiers. Given a model distribution $p(x, y)$, with the observation $y$ and the target $x$, one computes generative classifiers by firstly considering $p(x, y)$ and then using the Bayes rule to calculate $p(x | y)$. A discriminative model is directly given by $p(x | y)$, which is used to compute discriminative classifiers. However, recent works showed that the Bayesian Maximum Posterior classifier defined from the Naive Bayes (NB) or Hidden Markov Chain (HMC), both generative models, can also match the discriminative classifier definition. Thus, there are situations in which dividing classifiers into "generative" and "discriminative" is somewhat misleading. Indeed, such a distinction is rather related to the way of computing classifiers, not to the classifiers themselves. We present a general theoretical result specifying how a generative classifier induced from a generative model can also be computed in a discriminative way from the same model. Examples of NB and HMC are found again as particular cases, and we apply the general result to two original extensions of NB, and two extensions of HMC, one of which being original. Finally, we shortly illustrate the interest of the new discriminative way of computing classifiers in the Natural Language Processing (NLP) framework.