# Evolutionary Variational Optimization of Generative Models

arXiv: https://arxiv.org/abs/2012.12294 · HTML: https://mlsanity.com/paper/2012.12294/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2020.

## Built on by (most cited first, 4 of 4)

- [Variational Sparse Coding with Learned Thresholding](https://mlsanity.com/paper/2205.03665/) (2022)
- [Multi-objective evolutionary GAN for tabular data synthesis](https://mlsanity.com/paper/2404.10176/) (2024)
- [Sublinear Variational Optimization of Gaussian Mixture Models with Millions to Billions of Parameters](https://mlsanity.com/paper/2501.12299/) (2025)
- [Disentanglement of Sources in a Multi-Stream Variational Autoencoder](https://mlsanity.com/paper/2510.15669/) (2025)

## Abstract (arXiv)

We combine two popular optimization approaches to derive learning algorithms for generative models: variational optimization and evolutionary algorithms. The combination is realized for generative models with discrete latents by using truncated posteriors as the family of variational distributions. The variational parameters of truncated posteriors are sets of latent states. By interpreting these states as genomes of individuals and by using the variational lower bound to define a fitness, we can apply evolutionary algorithms to realize the variational loop. The used variational distributions are very flexible and we show that evolutionary algorithms can effectively and efficiently optimize the variational bound. Furthermore, the variational loop is generally applicable ("black box") with no analytical derivations required. To show general applicability, we apply the approach to three generative models (we use noisy-OR Bayes Nets, Binary Sparse Coding, and Spike-and-Slab Sparse Coding). To demonstrate effectiveness and efficiency of the novel variational approach, we use the standard competitive benchmarks of image denoising and inpainting. The benchmarks allow quantitative comparisons to a wide range of methods including probabilistic approaches, deep deterministic and generative networks, and non-local image processing methods. In the category of "zero-shot" learning (when only the corrupted image is used for training), we observed the evolutionary variational algorithm to significantly improve the state-of-the-art in many benchmark settings. For one well-known inpainting benchmark, we also observed state-of-the-art performance across all categories of algorithms although we only train on the corrupted image. In general, our investigations highlight the importance of research on optimization methods for generative models to achieve performance improvements.