mlsanityData to 7 Oct 2026

Stochastic Gradient Hamiltonian Monte Carlo

arXiv 1402.4102 ↗First posted 17 Feb 2014stat.ME cs.LG stat.MLcited by 341

Not on the map. Why?

Abstract (arXiv)

Hamiltonian Monte Carlo (HMC) sampling methods provide a mechanism for defining distant proposals with high acceptance probabilities in a Metropolis-Hastings framework, enabling more efficient exploration of the state space than standard random-walk proposals. The popularity of such methods has grown significantly in recent years. However, a limitation of HMC methods is the required gradient computation for simulation of the Hamiltonian dynamical system-such computation is infeasible in problems involving a large sample size or streaming data. Instead, we must rely on a noisy gradient estimate computed from a subset of the data. In this paper, we explore the properties of such a stochastic gradient HMC approach. Surprisingly, the natural implementation of the stochastic approximation can be arbitrarily bad. To address this problem we introduce a variant that uses second-order Langevin dynamics with a friction term that counteracts the effects of the noisy gradient, maintaining the desired target distribution as the invariant distribution. Results on simulated data validate our theory. We also provide an application of our methods to a classification task using neural networks and to online Bayesian matrix factorization.

Key facts. Cited by 341 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Feb 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 2; 2021: 53; 2022: 65; 2023: 73; 2024: 65; 2025: 53; 2026: 30.

341 papers.

Sort:

By area:

  1. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 307
  2. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusioncited by 230
  3. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  4. 2021HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPOcited by 111
  5. 2021Bayesian imaging using Plug & Play priors: when Langevin meets Tweediecited by 96
  6. 2023PFNs4BO: In-Context Learning for Bayesian Optimizationcited by 70
  7. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 60
  8. 2023Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimizationcited by 57
  9. 2023A Study of Bayesian Neural Network Surrogates for Bayesian Optimizationcited by 50
  10. 2022Sample-dependent Adaptive Temperature Scaling for Improved Calibrationcited by 48
  11. 2022On Uncertainty, Tempering, and Data Augmentation in Bayesian Classificationcited by 46
  12. 2022Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priorscited by 43
38 more
  1. 2021Heavy Ball Neural Ordinary Differential Equationscited by 42
  2. 2021MCMC Variational Inference via Uncorrected Hamiltonian Annealingcited by 39
  3. 2021Learning Functional Priors and Posteriors from Data and Physicscited by 37
  4. 2021Differentiable Annealed Importance Sampling and the Perils of Gradient Noisecited by 36
  5. 2023BayesDAG: Gradient-Based Posterior Inference for Causal Discoverycited by 33
  6. 2021Exact Langevin Dynamics with Stochastic Gradientscited by 30
  7. 2022DeepONet-Grid-UQ: A Trustworthy Deep Operator Framework for Predicting the Power Grid's Post-Fault Trajectoriescited by 30
  8. 2023BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inferencecited by 30
  9. 2022Adapting the Linearised Laplace Model Evidence for Modern Deep Learningcited by 29
  10. 2022Improving Task-free Continual Learning by Distributionally Robust Memory Evolutioncited by 29
  11. 2022Copula Conformal Prediction for Multi-step Time Series Forecastingcited by 28
  12. 2023Quantification of Uncertainty with Adversarial Modelscited by 28
  13. 2024Conformalized-DeepONet: A Distribution-Free Framework for Uncertainty Quantification in Deep Operator Networkscited by 28
  14. 2022RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustnesscited by 27
  15. 2022Accelerated Linearized Laplace Approximation for Bayesian Deep Learningcited by 27
  16. 2022Sparsity Agnostic Depth Completioncited by 27
  17. 2023Transfer Learning for Bayesian Optimization: A Surveycited by 27
  18. 2021BORE: Bayesian Optimization by Density-Ratio Estimationcited by 26
  19. 2022BaCaDI: Bayesian Causal Discovery with Unknown Interventionscited by 26
  20. 2023A Primer on Bayesian Neural Networks: Review and Debatescited by 26
  21. 2022Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgottencited by 25
  22. 2022Conformal Prediction with Temporal Quantile Adjustmentscited by 25
  23. 2021A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applicationscited by 24
  24. 2022FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulationcited by 24
  25. 2022Bayesian autoencoders for data-driven discovery of coordinates, governing equations and fundamental constantscited by 24
  26. 2022BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networkscited by 23
  27. 2021Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effectcited by 22
  28. 2021Accelerated replica exchange stochastic gradient Langevin diffusion enhanced Bayesian DeepONet for solving noisy parametric PDEscited by 22
  29. 2023Uncertainty-aware Surrogate Models for Airfoil Flow Simulations with Denoising Diffusion Probabilistic Modelscited by 22
  30. 2024CPR: Retrieval Augmented Generation for Copyright Protectioncited by 22
  31. 2024A Meta-Learning Approach to Bayesian Causal Discoverycited by 22
  32. 2022Diagnose Like a Radiologist: Hybrid Neuro-Probabilistic Reasoning for Attribute-Based Medical Image Diagnosiscited by 21
  33. 2022Knowledge Removal in Sampling-based Bayesian Inferencecited by 20
  34. 2022Generalized Variational Inference in Function Spaces: Gaussian Measures meet Bayesian Deep Learningcited by 20
  35. 2022Particle-based Variational Inference with Preconditioned Functional Gradient Flowcited by 20
  36. 2024LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networkscited by 20
  37. 2022Maximizing information from chemical engineering data sets: Applications to machine learningcited by 17
  38. 2023Variational Linearized Laplace Approximation for Bayesian Deep Learningcited by 17

50 most cited of 341 All 341 (JSON)