# Generalized Regression with Conditional GANs

arXiv: https://arxiv.org/abs/2404.13500 · HTML: https://mlsanity.com/paper/2404.13500/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 21 Apr 2024.

## Builds on (most cited first, 10 of 10)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed Distributions](https://mlsanity.com/paper/2101.09113/) (2021)
- [Skeletal Feature Compensation for Imitation Learning with Embodiment Mismatch](https://mlsanity.com/paper/2104.07810/) (2021)
- [Benchmarking Regression Methods: A comparison with CGAN](https://mlsanity.com/paper/1905.12868/) (2019)
- [Personalized Promotion Decision Making Based on Direct and Enduring Effect Predictions](https://mlsanity.com/paper/2207.14798/) (2022)
- [On some theoretical limitations of Generative Adversarial Networks](https://mlsanity.com/paper/2110.10915/) (2021)
- [ABC: Adversarial Behavioral Cloning for Offline Mode-Seeking Imitation Learning](https://mlsanity.com/paper/2211.04005/) (2022)

## Abstract (arXiv)

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 whose outputs, when paired with the corresponding inputs, are indistinguishable from feature-label pairs in the training dataset. We show that this approach to regression makes fewer assumptions on the distribution of the data we are fitting to and, therefore, has better representation capabilities. We draw parallels with generalized linear models in statistics and show how our proposal serves as an extension of them to neural networks. 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 with real-world heavy-tailed regression datasets. To make our work more reproducible, we release our source code. Link to repository: https://anonymous.4open.science/r/regressGAN-7B71/