# Bayesian Generative Adversarial Networks via Gaussian Approximation for Tabular Data Synthesis

arXiv: https://arxiv.org/abs/2602.21948 · HTML: https://mlsanity.com/paper/2602.21948/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 55 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [A Simple Baseline for Bayesian Uncertainty in Deep Learning](https://mlsanity.com/paper/1902.02476/) (2019)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Laplace Redux -- Effortless Bayesian Deep Learning](https://mlsanity.com/paper/2106.14806/) (2021)
- [Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks](https://mlsanity.com/paper/1512.07666/) (2015)
- [PacGAN: The power of two samples in generative adversarial networks](https://mlsanity.com/paper/1712.04086/) (2017)
- [Noisy Natural Gradient as Variational Inference](https://mlsanity.com/paper/1712.02390/) (2017)
- [VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data](https://mlsanity.com/paper/2006.11941/) (2020)
- [Metropolis-Hastings Generative Adversarial Networks](https://mlsanity.com/paper/1811.11357/) (2018)
- [Bayesian GAN](https://mlsanity.com/paper/1705.09558/) (2017)
- [Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression](https://mlsanity.com/paper/2109.08248/) (2021)
- [Exponential Family Variational Flow Matching for Tabular Data Generation](https://mlsanity.com/paper/2506.05940/) (2025)
- [PAC-Bayesian Generalization Bounds for Adversarial Generative Models](https://mlsanity.com/paper/2302.08942/) (2023)
- [Adversarial Training with Stochastic Weight Average](https://mlsanity.com/paper/2009.10526/) (2020)
- [Flow Matching for Tabular Data Synthesis](https://mlsanity.com/paper/2512.00698/) (2025)
- [Generative Adversarial Networks for Synthetic Data Generation: A Comparative Study](https://mlsanity.com/paper/2112.01925/) (2021)
- [Multi-objective evolutionary GAN for tabular data synthesis](https://mlsanity.com/paper/2404.10176/) (2024)
- [Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecasting](https://mlsanity.com/paper/2112.02622/) (2021)
- [Object Segmentation using Pixel-wise Adversarial Loss](https://mlsanity.com/paper/1909.10341/) (2019)

## Abstract (arXiv)

Generative Adversarial Networks (GAN) have been used in many studies to synthesise mixed tabular data. Conditional tabular GAN (CTGAN) have been the most popular variant but struggle to effectively navigate the risk-utility trade-off. Bayesian GAN have received less attention for tabular data, but have been explored with unstructured data such as images and text. The most used technique employed in Bayesian GAN is Markov Chain Monte Carlo (MCMC), but it is computationally intensive, particularly in terms of weight storage. In this paper, we introduce Gaussian Approximation of CTGAN (GACTGAN), an integration of the Bayesian posterior approximation technique using Stochastic Weight Averaging-Gaussian (SWAG) within the CTGAN generator to synthesise tabular data, reducing computational overhead after the training phase. We demonstrate that GACTGAN yields better synthetic data compared to CTGAN, achieving better preservation of tabular structure and inferential statistics with less privacy risk. These results highlight GACTGAN as a simpler, effective implementation of Bayesian tabular synthesis.