Generalized Regression with Conditional GANs

Regression is typically treated as a curve-fitting process where the goal is to fit a prediction function to data. With the help of conditional generative adversarial networks, we propose to solve this age-old problem in a different way; we aim to learn a prediction function such that its outputs when paired with the corresponding inputs, are indistinguishable from feature-label pairs in the training dataset. We show that this approach makes fewer assumptions on the distribution of the data we are fitting to and, therefore, has better representation capabilities. We demonstrate the superiority of this new approach to standard regression with experiments on multiple synthetic and publicly available real-world datasets, finding encouraging results, especially for the task of heavy-tailed regression. We also address limitations and point out avenues for future research.