mlsanityData to 7 Oct 2026

NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport

arXiv 1903.03704 ↗First posted 9 Mar 2019stat.CO stat.MLcited by 73

Not on the map. Why?

Abstract (arXiv)

Hamiltonian Monte Carlo is a powerful algorithm for sampling from difficult-to-normalize posterior distributions. However, when the geometry of the posterior is unfavorable, it may take many expensive evaluations of the target distribution and its gradient to converge and mix. We propose neural transport (NeuTra) HMC, a technique for learning to correct this sort of unfavorable geometry using inverse autoregressive flows (IAF), a powerful neural variational inference technique. The IAF is trained to minimize the KL divergence from an isotropic Gaussian to the warped posterior, and then HMC sampling is performed in the warped space. We evaluate NeuTra HMC on a variety of synthetic and real problems, and find that it significantly outperforms vanilla HMC both in time to reach the stationary distribution and asymptotic effective-sample-size rates.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 8; 2023: 11; 2024: 16; 2025: 10; 2026: 14.

73 papers.

Sort:

By area:

  1. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  2. 2021Path Integral Sampler: a stochastic control approach for samplingcited by 175
  3. 2024Particle Denoising Diffusion Samplercited by 63
  4. 2021Density Ratio Estimation via Infinitesimal Classificationcited by 59
  5. 2024Improved off-policy training of diffusion samplerscited by 47
  6. 2021Solution of Physics-based Bayesian Inverse Problems with Deep Generative Priorscited by 29
  7. 2021Towards Understanding the Generative Capability of Adversarially Robust Classifierscited by 26
  8. 2022Aspects of scaling and scalability for flow-based sampling of lattice QCDcited by 26
  9. 2023Advances in machine-learning-based sampling motivated by lattice quantum chromodynamicscited by 23
  10. 2021Local-Global MCMC kernels: the best of both worldscited by 21
  11. 2023On Sampling with Approximate Transport Mapscited by 20
  12. 2023Improving Gradient-guided Nested Sampling for Posterior Inferencecited by 14
38 more
  1. 2023Energy-Guided Continuous Entropic Barycenter Estimation for General Costscited by 12
  2. 2024Amortized Bayesian Multilevel Modelscited by 12
  3. 2021Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descentcited by 10
  4. 2022Deterministic Langevin Monte Carlo with Normalizing Flows for Bayesian Inferencecited by 10
  5. 2021Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Samplingcited by 9
  6. 2022Wide Bayesian neural networks have a simple weight posterior: theory and accelerated samplingcited by 9
  7. 2024Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flowscited by 9
  8. 2022Transport Score Climbing: Variational Inference Using Forward KL and Adaptive Neural Transportcited by 8
  9. 2023Transition Path Sampling with Boltzmann Generator-based MCMC Movescited by 8
  10. 2021Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMCcited by 7
  11. 2021Deep Learning Hamiltonian Monte Carlocited by 7
  12. 2023Normalizing flow sampling with Langevin dynamics in the latent spacecited by 7
  13. 2024Importance Corrected Neural JKO Samplingcited by 7
  14. 2022Latent Space Diffusion Models of Cryo-EM Structurescited by 6
  15. 2024Hamiltonian Score Matching and Generative Flowscited by 6
  16. 2021Entropy-based adaptive Hamiltonian Monte Carlocited by 5
  17. 2021Bootstrap Your Flowcited by 5
  18. 2022Transport Reversible Jump Proposalscited by 5
  19. 2024Quasi-Bayes meets Vinescited by 5
  20. 2024Disentangling impact of capacity, objective, batchsize, estimators, and step-size on flow VIcited by 5
  21. 2022Principal Manifold Flowscited by 4
  22. 2023Automatically Marginalized MCMC in Probabilistic Programmingcited by 4
  23. 2023Balanced Training of Energy-Based Models with Adaptive Flow Samplingcited by 4
  24. 2023Self-Tuning Hamiltonian Monte Carlo for Accelerated Samplingcited by 4
  25. 2023Efficient Multimodal Sampling via Tempered Distribution Flowcited by 3
  26. 2024Amortized Bayesian Workflowcited by 3
  27. 2025Model-Informed Flows for Bayesian Inferencecited by 3
  28. 2025Learning Geometry and Topology via Multi-Chart Flowscited by 3
  29. 2021Reparameterized Sampling for Generative Adversarial Networkscited by 2
  30. 2025FlowVAT: Normalizing Flow Variational Inference with Affine-Invariant Temperingcited by 2
  31. 2021Semi-Empirical Objective Functions for MCMC Proposal Optimizationcited by 1
  32. 2022Reconstructing the Universe with Variational self-Boosted Samplingcited by 1
  33. 2024Fast Bayesian Inference for Neutrino Non-Standard Interactions at Dark Matter Direct Detection Experimentscited by 1
  34. 2024Ai-Sampler: Adversarial Learning of Markov kernels with involutive mapscited by 1
  35. 2024SoftCVI: Contrastive variational inference with self-generated soft labelscited by 1
  36. 2024Hamiltonian Monte Carlo Inference of Marginalized Linear Mixed-Effects Modelscited by 1
  37. 2024Empirical evaluation of normalizing flows in Markov Chain Monte Carlocited by 1
  38. 2025Enhanced Importance Sampling through Latent Space Exploration in Normalizing Flowscited by 1

50 most cited of 73 All 73 (JSON)