mlsanityData to 7 Oct 2026

Exact Langevin Dynamics with Stochastic Gradients

arXiv 2102.01691 ↗First posted 2 Feb 2021stat.ML cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

Stochastic gradient Markov Chain Monte Carlo algorithms are popular samplers for approximate inference, but they are generally biased. We show that many recent versions of these methods (e.g. Chen et al. (2014)) cannot be corrected using Metropolis-Hastings rejection sampling, because their acceptance probability is always zero. We can fix this by employing a sampler with realizable backwards trajectories, such as Gradient-Guided Monte Carlo (Horowitz, 1991), which generalizes stochastic gradient Langevin dynamics (Welling and Teh, 2011) and Hamiltonian Monte Carlo. We show that this sampler can be used with stochastic gradients, yielding nonzero acceptance probabilities, which can be computed even across multiple steps.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 10 of its 26 references that are in the map. First posted on arXiv 2 Feb 2021.

Builds on

10 of 26 references.

References · 10

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2014Stochastic Gradient Hamiltonian Monte Carlocited by 341
  3. 2019Cyclical Stochastic Gradient MCMC for Bayesian Deep Learningcited by 203
  4. 2020Stochastic Normalizing Flowscited by 156
  5. 2015A Complete Recipe for Stochastic Gradient MCMCcited by 146
  6. 2020AMAGOLD: Amortized Metropolis Adjustment for Efficient Stochastic Gradient MCMCcited by 13
  7. 2014Hamiltonian Monte Carlo Without Detailed Balancecited by 10
  8. 2019Partitioned integrators for thermodynamic parameterization of neural networkscited by 9
  9. 2016Irreversible Samplers from Jump and Continuous Markov Processescited by 5
  10. 2018Langevin Markov Chain Monte Carlo with stochastic gradientscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 3; 2023: 4; 2024: 4; 2025: 5; 2026: 3.

30 papers.

Sort:

By area:

  1. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
  2. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 307
  3. 2021Bayesian Neural Network Priors Revisitedcited by 121
  4. 2021Repulsive Deep Ensembles are Bayesiancited by 103
  5. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  6. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 60
  7. 2021Data augmentation in Bayesian neural networks and the cold posterior effectcited by 36
  8. 2021On Stein Variational Neural Network Ensemblescited by 21
  9. 2021BNNpriors: A library for Bayesian neural network inference with different prior distributionscited by 20
  10. 2024Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Modelscited by 20
  11. 2021Neural Variational Gradient Descentcited by 19
  12. 2023Improving Neural Additive Models with Bayesian Principlescited by 15
18 more
  1. 2021Pathologies in priors and inference for Bayesian transformerscited by 13
  2. 2022Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and Pitfallscited by 11
  3. 2023Promises and Pitfalls of the Linearized Laplace in Bayesian Optimizationcited by 10
  4. 2021Deep Classifiers with Label Noise Modeling and Distance Awarenesscited by 8
  5. 2026Can Microcanonical Langevin Dynamics Leverage Mini-Batch Gradient Noise?cited by 6
  6. 2023FedBIAD: Communication-Efficient and Accuracy-Guaranteed Federated Learning with Bayesian Inference-Based Adaptive Dropoutcited by 4
  7. 2025Contextual Similarity Distillation: Ensemble Uncertainties with a Single Modelcited by 3
  8. 2024Functional Stochastic Gradient MCMC for Bayesian Neural Networkscited by 2
  9. 2025Parameter Expanded Stochastic Gradient Markov Chain Monte Carlocited by 2
  10. 2022Data Subsampling for Bayesian Neural Networkscited by 1
  11. 2025JaxSGMC: Modular stochastic gradient MCMC in JAXcited by 1
  12. 2025Accelerating Hamiltonian Monte Carlo for Bayesian Inference in Neural Networks and Neural Operatorscited by 1
  13. 2026Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learningcited by 1
  14. 2022Complexity from Adaptive-Symmetries Breaking: Global Minima in the Statistical Mechanics of Deep Neural Networkscited by 0
  15. 2023Uncertainty in Graph Contrastive Learning with Bayesian Neural Networkscited by 0
  16. 2024Stein Variational Newton Neural Network Ensemblescited by 0
  17. 2025Priors Matter: Addressing Misspecification in Bayesian Deep Q-Learningcited by 0
  18. 2026On the Equivalence of Random Network Distillation, Deep Ensembles, and Bayesian Inferencecited by 0