# Stein Variational Evolution Strategies

arXiv: https://arxiv.org/abs/2410.10390 · HTML: https://mlsanity.com/paper/2410.10390/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 68 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 30 of 38)

- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm](https://mlsanity.com/paper/1608.04471/) (2016)
- [New insights and perspectives on the natural gradient method](https://mlsanity.com/paper/1412.1193/) (2014)
- [Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation](https://mlsanity.com/paper/2106.13281/) (2021)
- [The CMA Evolution Strategy: A Tutorial](https://mlsanity.com/paper/1604.00772/) (2016)
- [Predictive Entropy Search for Efficient Global Optimization of Black-box Functions](https://mlsanity.com/paper/1406.2541/) (2014)
- [A Stein variational Newton method](https://mlsanity.com/paper/1806.03085/) (2018)
- [Message Passing Stein Variational Gradient Descent](https://mlsanity.com/paper/1711.04425/) (2017)
- [Leveraging exploration in off-policy algorithms via normalizing flows](https://mlsanity.com/paper/1905.06893/) (2019)
- [Stein Variational Policy Gradient](https://mlsanity.com/paper/1704.02399/) (2017)
- [evosax: JAX-based Evolution Strategies](https://mlsanity.com/paper/2212.04180/) (2022)
- [Stein Variational Gradient Descent With Matrix-Valued Kernels](https://mlsanity.com/paper/1910.12794/) (2019)
- [Discovering Many Diverse Solutions with Bayesian Optimization](https://mlsanity.com/paper/2210.10953/) (2022)
- [Stein Variational Model Predictive Control](https://mlsanity.com/paper/2011.07641/) (2020)
- [EvoJAX: Hardware-Accelerated Neuroevolution](https://mlsanity.com/paper/2202.05008/) (2022)
- [Annealed Stein Variational Gradient Descent](https://mlsanity.com/paper/2101.09815/) (2021)
- [Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions](https://mlsanity.com/paper/1901.08659/) (2019)
- [Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning](https://mlsanity.com/paper/1902.00925/) (2019)
- [On Stein Variational Neural Network Ensembles](https://mlsanity.com/paper/2106.10760/) (2021)
- [Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence Theory](https://mlsanity.com/paper/1809.01293/) (2018)
- [Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian](https://mlsanity.com/paper/2011.06505/) (2020)
- [Neural Variational Gradient Descent](https://mlsanity.com/paper/2107.10731/) (2021)
- [Diffusion Models are Evolutionary Algorithms](https://mlsanity.com/paper/2410.02543/) (2024)
- [Variational Inference based on Robust Divergences](https://mlsanity.com/paper/1710.06595/) (2017)
- [Trust-Region Variational Inference with Gaussian Mixture Models](https://mlsanity.com/paper/1907.04710/) (2019)
- [Stein Variational Gradient Descent Without Gradient](https://mlsanity.com/paper/1806.02775/) (2018)
- [Grassmann Stein Variational Gradient Descent](https://mlsanity.com/paper/2202.03297/) (2022)
- [VP-STO: Via-point-based Stochastic Trajectory Optimization for Reactive Robot Behavior](https://mlsanity.com/paper/2210.04067/) (2022)
- [ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages](https://mlsanity.com/paper/2306.01460/) (2023)

## Built on by (most cited first, 2 of 2)

- [Trajectory First: A Curriculum for Discovering Diverse Policies](https://mlsanity.com/paper/2506.01568/) (2025)
- [Stein Variational Black-Box Combinatorial Optimization](https://mlsanity.com/paper/2604.15837/) (2026)

## Abstract (arXiv)

Stein Variational Gradient Descent (SVGD) is a highly efficient method to sample from an unnormalized probability distribution. However, the SVGD update relies on gradients of the log-density, which may not always be available. Existing gradient-free versions of SVGD make use of simple Monte Carlo approximations or gradients from surrogate distributions, both with limitations. To improve gradient-free Stein variational inference, we combine SVGD steps with evolution strategy (ES) updates. Our results demonstrate that the resulting algorithm generates high-quality samples from unnormalized target densities without requiring gradient information. Compared to prior gradient-free SVGD methods, we find that the integration of the ES update in SVGD significantly improves the performance on multiple challenging benchmark problems.