mlsanityData to 14 Oct 2026

Stein Variational Evolution Strategies

arXiv 2410.10390 ↗First posted 14 Oct 2024cs.LG cs.AI cs.NEcited by 2

Not on the map. Why?

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.

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

38 of 68 references.

References · 38

  1. 2017Visualizing the Loss Landscape of Neural Netscited by 1,130
  2. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 574
  3. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 507
  4. 2014New insights and perspectives on the natural gradient methodcited by 443
  5. 2021Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulationcited by 407
  6. 2016The CMA Evolution Strategy: A Tutorialcited by 377
  7. 2014Predictive Entropy Search for Efficient Global Optimization of Black-box Functionscited by 204
  8. 2018A Stein variational Newton methodcited by 50
  9. 2017Message Passing Stein Variational Gradient Descentcited by 47
  10. 2019Leveraging exploration in off-policy algorithms via normalizing flowscited by 46
  11. 2017Stein Variational Policy Gradientcited by 44
  12. 2022evosax: JAX-based Evolution Strategiescited by 41
26 more
  1. 2019Stein Variational Gradient Descent With Matrix-Valued Kernelscited by 32
  2. 2022Discovering Many Diverse Solutions with Bayesian Optimizationcited by 31
  3. 2020Stein Variational Model Predictive Controlcited by 30
  4. 2022EvoJAX: Hardware-Accelerated Neuroevolutioncited by 29
  5. 2021Annealed Stein Variational Gradient Descentcited by 26
  6. 2019Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensionscited by 21
  7. 2019Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learningcited by 21
  8. 2021On Stein Variational Neural Network Ensemblescited by 21
  9. 2018Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence Theorycited by 20
  10. 2020Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessiancited by 20
  11. 2021Neural Variational Gradient Descentcited by 19
  12. 2024Diffusion Models are Evolutionary Algorithmscited by 17
  13. 2017Variational Inference based on Robust Divergencescited by 15
  14. 2019Trust-Region Variational Inference with Gaussian Mixture Modelscited by 14
  15. 2018Stein Variational Gradient Descent Without Gradientcited by 12
  16. 2022Grassmann Stein Variational Gradient Descentcited by 12
  17. 2022VP-STO: Via-point-based Stochastic Trajectory Optimization for Reactive Robot Behaviorcited by 10
  18. 2023ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantagescited by 10
  19. 2022Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environmentscited by 9
  20. 2023Constrained Stein Variational Trajectory Optimizationcited by 8
  21. 2020Stein Self-Repulsive Dynamics: Benefits From Past Samplescited by 6
  22. 2021Stein ICP for Uncertainty Estimation in Point Cloud Matchingcited by 6
  23. 2023Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategiescited by 5
  24. 2023STAMP: Differentiable Task and Motion Planning via Stein Variational Gradient Descentcited by 4
  25. 2024NLP Sampling: Combining MCMC and NLP Methods for Diverse Constrained Samplingcited by 4
  26. 2023Path Signatures for Diversity in Probabilistic Trajectory Optimisationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Trajectory First: A Curriculum for Discovering Diverse Policiescited by 0
  2. 2026Stein Variational Black-Box Combinatorial Optimizationcited by 0