Research map / Optimization / Optimizers
Stein variational gradient descent
Transports particles with kernelized Stein variational updates for Bayesian inference, with analysis and extensions.
47 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Optimizers, keyword cluster “variational · sampling · inference”
State History Tried Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
10 papers in 2023–24 and 6 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 4.1% to 2.1%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm (NeurIPS 2016 · 307 citations)
- 2017 · Stein Variational Gradient Descent as Gradient Flow (NeurIPS 2017 · 112 citations)
- 2018 · A Stein variational Newton method (NeurIPS 2018 · 39 citations)
- 2019 · Stein Variational Gradient Descent With Matrix-Valued Kernels (NeurIPS 2019 · 41 citations)
- 2020 · A Non-Asymptotic Analysis for Stein Variational Gradient Descent (NeurIPS 2020 · 28 citations)
- 2021 · Profiling Pareto Front With Multi-Objective Stein Variational Gradient Descent (NeurIPS 2021 · 11 citations)
- 2022 · Variational Wasserstein gradient flow (ICML 2022 · 7 citations)
- 2023 · Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descent (NeurIPS 2023 · 3 citations)
- 2024 · Semi-Discrete Optimal Transport: Nearly Minimax Estimation With Stochastic Gradient Descent and Adaptive Entropic Regularization (NeurIPS 2024 · 0 citations)
- 2025 · Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport (NeurIPS 2025 · 0 citations)
- 2026 · Stochastic Gradient Variational Inference with Price's Gradient Estimator from Bures-Wasserstein to Parameter Space (ICML 2026 · 0 citations)
Earliest papers here
- Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm (NeurIPS 2016 · 307 citations)
- Black-Box Alpha Divergence Minimization (ICML 2016 · 40 citations)
- Stein Variational Gradient Descent as Gradient Flow (NeurIPS 2017 · 112 citations)
What has been tried
40 papers here report 334 measured changes (a component added, removed or swapped, compared with a baseline): helped 65%, no clear effect 11%, hurt 19%, mixed 4%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Use weighted averaging with \omega =2 instead of uniform averaging | Synthetic Examples 2 and 3 · potential estimation error | orders of magnitude | Helped | Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport (NeurIPS 2025 · 0 citations) |
| Use mini-batching with nb = 16 | Example 2 · potential estimation error | an order of magnitude lower | Helped | Semi-Discrete Optimal Transport: Nearly Minimax Estimation With Stochastic Gradient Descent and Adaptive Entropic Regularization (NeurIPS 2024 · 0 citations) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 16 papers; from OpenAlex and the papers' affiliations).
- North Carolina State University · 2 papers
Use it
Download BibTeX of 27 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Stochastic gradient MCMC (142 papers)
- Natural gradient and Fisher approximations (77 papers)
- Zeroth-order training methods (23 papers)
Elsewhere in the topic
- Surrogate losses and robust solvers (119 papers)
- Differentiating through embedded optimization (117 papers)
- Constrained and non-backprop training (97 papers)
- Memory-efficient LLM optimizers (79 papers)
- Adam convergence and adaptive learning rates (78 papers)
- Randomized gradient estimation (77 papers)
- SGD momentum and step-size schedules (72 papers)
- Second-order and structured preconditioning (70 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).