mlsanityData to 14 Oct 2026

Learning to Draw Samples with Amortized Stein Variational Gradient Descent

arXiv 1707.06626 ↗First posted 20 Jul 2017stat.MLcited by 28

Not on the map. Why?

Abstract (arXiv)

We propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference. Our method is based on iteratively adjusting the neural network parameters so that the output changes along a Stein variational gradient direction (Liu & Wang, 2016) that maximally decreases the KL divergence with the target distribution. Our method works for any target distribution specified by their unnormalized density function, and can train any black-box architectures that are differentiable in terms of the parameters we want to adapt. We demonstrate our method with a number of applications, including variational autoencoder (VAE) with expressive encoders to model complex latent space structures, and hyper-parameter learning of MCMC samplers that allows Bayesian inference to adaptively improve itself when seeing more data.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 5; 2023: 7; 2024: 4; 2025: 3; 2026: 4.

28 papers.

Sort:

By area:

  1. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  2. 2021Tractable Regularization of Probabilistic Circuitscited by 39
  3. 2024DreamFlow: High-Quality Text-to-3D Generation by Approximating Probability Flowcited by 26
  4. 2022Particle-based Variational Inference with Preconditioned Functional Gradient Flowcited by 20
  5. 2022Sliced Wasserstein Variational Inferencecited by 18
  6. 2024S2AC: Energy-Based Reinforcement Learning with Stein Soft Actor Criticcited by 18
  7. 2021Sampling with Mirrored Stein Operatorscited by 17
  8. 2024Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descentcited by 14
  9. 2023Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descentcited by 13
  10. 2023Fully Bayesian Autoencoders with Latent Sparse Gaussian Processescited by 9
  11. 2023Coin Sampling: Gradient-Based Bayesian Inference without Learning Ratescited by 8
  12. 2021Multi-Discriminator Sobolev Defense-GAN Against Adversarial Attacks for End-to-End Speech Systemscited by 4
16 more
  1. 2021Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inferencecited by 4
  2. 2021Stein Variational Gradient Descent with Multiple Kernelcited by 4
  3. 2026Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Modelscited by 4
  4. 2023A Semi-Bayesian Nonparametric Estimator of the Maximum Mean Discrepancy Measure: Applications in Goodness-of-Fit Testing and Generative Adversarial Networkscited by 3
  5. 2023Moreau-Yoshida Variational Transport: A General Framework For Solving Regularized Distributional Optimization Problemscited by 3
  6. 2026Uniform-in-time Propagation-of-Chaos for Stein Variational Gradient Descentcited by 2
  7. 2023Negotiated Reasoning: On Provably Addressing Relative Over-Generalizationcited by 1
  8. 2024ELBOing Stein: Variational Bayes with Stein Mixture Inferencecited by 1
  9. 2022RSD-GAN: Regularized Sobolev Defense GAN Against Speech-to-Text Adversarial Attackscited by 0
  10. 2022Towards Task-Prioritized Policy Compositioncited by 0
  11. 2022Posterior sampling with CNN-based, Plug-and-Play regularization with applications to Post-Stack Seismic Inversioncited by 0
  12. 2025Revisiting Unbiased Implicit Variational Inferencecited by 0
  13. 2025Semi-Implicit Variational Inference via Kernelized Path Gradient Descentcited by 0
  14. 2025Branching Stein Variational Gradient Descent for sampling multimodal distributionscited by 0
  15. 2026Refinement-based Flow Policy Optimizationcited by 0
  16. 2026Amortised Inference through One-Step Implicit Samplingcited by 0