mlsanityData to 14 Oct 2026

Generalizing Hamiltonian Monte Carlo with Neural Networks

arXiv 1711.09268 ↗First posted 25 Nov 2017stat.ML cs.AI cs.LGcited by 52

Not on the map. Why?

Abstract (arXiv)

We present a general-purpose method to train Markov chain Monte Carlo kernels, parameterized by deep neural networks, that converge and mix quickly to their target distribution. Our method generalizes Hamiltonian Monte Carlo and is trained to maximize expected squared jumped distance, a proxy for mixing speed. We demonstrate large empirical gains on a collection of simple but challenging distributions, for instance achieving a 106x improvement in effective sample size in one case, and mixing when standard HMC makes no measurable progress in a second. Finally, we show quantitative and qualitative gains on a real-world task: latent-variable generative modeling. We release an open source TensorFlow implementation of the algorithm.

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 17; 2022: 10; 2023: 10; 2024: 10; 2025: 1; 2026: 3.

52 papers.

Sort:

By area:

  1. 2020Denoising Diffusion Implicit Modelscited by 9,781
  2. 2022Flow Annealed Importance Sampling Bootstrapcited by 127
  3. 2023Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamicscited by 66
  4. 2022VeLO: Training Versatile Learned Optimizers by Scaling Upcited by 57
  5. 2022Practical tradeoffs between memory, compute, and performance in learned optimizerscited by 32
  6. 2021Solution of Physics-based Bayesian Inverse Problems with Deep Generative Priorscited by 29
  7. 2022Aspects of scaling and scalability for flow-based sampling of lattice QCDcited by 26
  8. 2024Training Neural Samplers with Reverse Diffusive KL Divergencecited by 21
  9. 2024S2AC: Energy-Based Reinforcement Learning with Stein Soft Actor Criticcited by 18
  10. 2021Unbiased Monte Carlo Cluster Updates with Autoregressive Neural Networkscited by 17
  11. 2021Efficient Bayesian Sampling Using Normalizing Flows to Assist Markov Chain Monte Carlo Methodscited by 16
  12. 2022Applications of Machine Learning to Lattice Quantum Field Theorycited by 14
38 more
  1. 2023Optimal Preconditioning and Fisher Adaptive Langevin Samplingcited by 14
  2. 2022Denoising MCMC for Accelerating Diffusion-Based Generative Modelscited by 13
  3. 2023Entropy-based Training Methods for Scalable Neural Implicit Samplercited by 13
  4. 2021Structured Stochastic Gradient MCMCcited by 12
  5. 2023Energy-Guided Continuous Entropic Barycenter Estimation for General Costscited by 12
  6. 2021Revisiting Bayesian Autoencoders with MCMCcited by 10
  7. 2022Enhanced gradient-based MCMC in discrete spacescited by 10
  8. 2021Bayesian graph convolutional neural networks via tempered MCMCcited by 9
  9. 2021Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Samplingcited by 9
  10. 2021Deep Learning Hamiltonian Monte Carlocited by 7
  11. 2021LSB: Local Self-Balancing MCMC in Discrete Spacescited by 7
  12. 2021Delayed rejection Hamiltonian Monte Carlo for sampling multiscale distributionscited by 7
  13. 2022Accelerating Hamiltonian Monte Carlo via Chebyshev Integration Timecited by 7
  14. 2024Energy based diffusion generator for efficient sampling of Boltzmann distributionscited by 7
  15. 2024Hamiltonian Score Matching and Generative Flowscited by 7
  16. 2023Zero-shot-Learning Cross-Modality Data Translation Through Mutual Information Guided Stochastic Diffusioncited by 6
  17. 2021Entropy-based adaptive Hamiltonian Monte Carlocited by 5
  18. 2021Bootstrap Your Flowcited by 5
  19. 2021Machine Learning in Nuclear Physicscited by 4
  20. 2023A Diffusion-based Method for Multi-turn Compositional Image Generationcited by 4
  21. 2023Machine Learning and the Future of Bayesian Computationcited by 4
  22. 2023Self-Tuning Hamiltonian Monte Carlo for Accelerated Samplingcited by 4
  23. 2024Learning to Explore for Stochastic Gradient MCMCcited by 4
  24. 2021LeapfrogLayers: A Trainable Framework for Effective Topological Samplingcited by 3
  25. 2021Reparameterized Sampling for Generative Adversarial Networkscited by 2
  26. 2022Bayesian Inference with Latent Hamiltonian Neural Networkscited by 2
  27. 2024Reliability Analysis of Complex Systems using Subset Simulations with Hamiltonian Neural Networkscited by 2
  28. 2021NEO: Non Equilibrium Sampling on the Orbit of a Deterministic Transformcited by 1
  29. 2021Semi-Empirical Objective Functions for MCMC Proposal Optimizationcited by 1
  30. 2024Ai-Sampler: Adversarial Learning of Markov kernels with involutive mapscited by 1
  31. 2025Training neural control variates using correlated configurationscited by 1
  32. 2022Toward Unlimited Self-Learning MCMC with Parallel Adaptive Annealingcited by 0
  33. 2023Quantification of Predictive Uncertainty via Inference-Time Samplingcited by 0
  34. 2023Learning variational autoencoders via MCMC speed measurescited by 0
  35. 2024Repelling-Attracting Hamiltonian Monte Carlocited by 0
  36. 2024Neural Surrogate HMC: On Using Neural Likelihoods for Hamiltonian Monte Carlo in Simulation-Based Inferencecited by 0
  37. 2024Denoising Fisher Training For Neural Implicit Samplerscited by 0
  38. 2026Nonreversible Gauge Fields in Fokker--Planck Dynamics: Supersymmetric Hamiltonians and Learned Finite Forcescited by 0

50 most cited of 52 All 52 (JSON)