mlsanityData to 7 Oct 2026

Stochastic gradient Markov chain Monte Carlo

arXiv 1907.06986 ↗First posted 16 Jul 2019stat.CO stat.MLcited by 56

Not on the map. Why?

Abstract (arXiv)

Markov chain Monte Carlo (MCMC) algorithms are generally regarded as the gold standard technique for Bayesian inference. They are theoretically well-understood and conceptually simple to apply in practice. The drawback of MCMC is that in general performing exact inference requires all of the data to be processed at each iteration of the algorithm. For large data sets, the computational cost of MCMC can be prohibitive, which has led to recent developments in scalable Monte Carlo algorithms that have a significantly lower computational cost than standard MCMC. In this paper, we focus on a particular class of scalable Monte Carlo algorithms, stochastic gradient Markov chain Monte Carlo (SGMCMC) which utilises data subsampling techniques to reduce the per-iteration cost of MCMC. We provide an introduction to some popular SGMCMC algorithms and review the supporting theoretical results, as well as comparing the efficiency of SGMCMC algorithms against MCMC on benchmark examples. The supporting R code is available online.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 11; 2023: 8; 2024: 12; 2025: 9; 2026: 10.

56 papers.

Sort:

By area:

  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  2. 2022Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisonscited by 169
  3. 2023Machine learning with data assimilation and uncertainty quantification for dynamical systems: a reviewcited by 74
  4. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 60
  5. 2021GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learningcited by 26
  6. 2022Particle algorithms for maximum likelihood training of latent variable modelscited by 26
  7. 2024A Comprehensive Survey on Evidential Deep Learning and Its Applicationscited by 25
  8. 2023Fairness through Aleatoric Uncertaintycited by 16
  9. 2024Scalable Bayesian Learning with posteriorscited by 13
  10. 2024Sampling from Bayesian Neural Network Posteriors with Symmetric Minibatch Splitting Langevin Dynamicscited by 12
  11. 2025Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Schedulercited by 12
  12. 2021Efficient and Generalizable Tuning Strategies for Stochastic Gradient MCMCcited by 11
38 more
  1. 2022Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and Pitfallscited by 11
  2. 2022Nonlinear Sufficient Dimension Reduction with a Stochastic Neural Networkcited by 10
  3. 2021Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibrationcited by 7
  4. 2022Bregman Proximal Langevin Monte Carlo via Bregman--Moreau Envelopescited by 7
  5. 2022SwISS: A Scalable Markov chain Monte Carlo Divide-and-Conquer Strategycited by 6
  6. 2021Bounding Wasserstein distance with couplingscited by 5
  7. 2023Coreset Markov Chain Monte Carlocited by 5
  8. 2022Tuning Stochastic Gradient Algorithms for Statistical Inference via Large-Sample Asymptoticscited by 4
  9. 2023Machine Learning and the Future of Bayesian Computationcited by 4
  10. 2023Non-Log-Concave and Nonsmooth Sampling via Langevin Monte Carlo Algorithmscited by 4
  11. 2024Bayesian Federated Learning with Hamiltonian Monte Carlo: Algorithm and Theorycited by 4
  12. 2022Benchmarking Bayesian neural networks and evaluation metrics for regression taskscited by 3
  13. 2022TEDL: A Two-stage Evidential Deep Learning Method for Classification Uncertainty Quantificationcited by 3
  14. 2021Asynchronous and Distributed Data Augmentation for Massive Data Settingscited by 2
  15. 2022Centered plug-in estimation of Wasserstein distancescited by 2
  16. 2024Robust Approximate Sampling via Stochastic Gradient Barker Dynamicscited by 2
  17. 2024General bounds on the quality of Bayesian coresetscited by 2
  18. 2024Functional Stochastic Gradient MCMC for Bayesian Neural Networkscited by 2
  19. 2024The Polynomial Stein Discrepancy for Assessing Moment Convergencecited by 2
  20. 2025Random Reshuffling for Stochastic Gradient Langevin Dynamicscited by 2
  21. 2026High-accuracy log-concave sampling with stochastic queriescited by 2
  22. 2026Bayesian Lottery Ticket Hypothesiscited by 2
  23. 2023Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite Modelscited by 1
  24. 2024Scalable and Calibrated Sampling for Bayesian Generalized Linear Mixed Model via Stochastic Gradient Markov Chain Monte Carlocited by 1
  25. 2024Stochastic Gradient Piecewise Deterministic Monte Carlo Samplerscited by 1
  26. 2025JaxSGMC: Modular stochastic gradient MCMC in JAXcited by 1
  27. 2025Pointwise confidence estimation in the non-linear ℓ2-regularized least squarescited by 1
  28. 2025Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regimecited by 1
  29. 2026Generalization Guarantees on Data-Driven Tuning of Gradient Descent with Langevin Updatescited by 1
  30. 2026Safe, Scalable, and Accurate Bayes Posterior Sampling for Large-Data Generalized Linear Mixed Modelscited by 1
  31. 2022Preferential Subsampling for Stochastic Gradient Langevin Dynamicscited by 0
  32. 2023MSS-PAE: Saving Autoencoder-based Outlier Detection from Unexpected Reconstructioncited by 0
  33. 2023Gibbs Sampling the Posterior of Neural Networkscited by 0
  34. 2024Diffusion Generative Modelling for Divide-and-Conquer MCMCcited by 0
  35. 2025Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Priorcited by 0
  36. 2025Variational Autoencoder for Generating Broader-Spectrum prior Proposals in Markov chain Monte Carlo Methodscited by 0
  37. 2025Kalman Bayesian Transformercited by 0
  38. 2025Improving the stability of the covariance-controlled adaptive Langevin thermostat for large-scale Bayesian samplingcited by 0

50 most cited of 56 All 56 (JSON)