Generative modelling in machine learning can aim at achieving different goals. The first, obvious one is that a generative model can be used to generate more data, to be used afterwards by another algorithm. While a generative model cannot create more information to solve the issue of having too small datasets, it could be used to solve anonymity questions. Typically, sharing a generative model trained on private data could allow the exploitation of the statistical property of this data without sharing the data itself (which can be protected by privacy matters for example).
Another goal is to use generative modelling to better understand the data at hand. This is based on the hypothesis that a model that successfully learned to generate (and generalize) a dataset should have internally learned some efficient and compressed representation of the information contained in the data. In this case, analysing a posteriori the learned representation may give us insights on the data itself.
The notion of a generative model however needs to be more formally specified, in order to work with. What does it mean for the model to generate data that "looks like" the original dataset? A mathematical formulation of that is necessary, in order to define a training objective that can be used efficiently. Having some expert rate the quality of all generated datapoints one by one is definitely not an option.
In this work, I have focused on two of the most widely used generative models based on deep neural networks: Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs), in order to compare them and understand their strengths and weaknesses.