mlsanityData to 14 Oct 2026

NETS: A Non-Equilibrium Transport Sampler

arXiv 2410.02711 ↗First posted 3 Oct 2024cs.LG cond-mat.stat-mech hep-latcited by 69

Not on the map. Why?

Cited by 30 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose an algorithm, termed the Non-Equilibrium Transport Sampler (NETS), to sample from unnormalized probability distributions. NETS can be viewed as a variant of annealed importance sampling (AIS) based on Jarzynski's equality, in which the stochastic differential equation used to perform the non-equilibrium sampling is augmented with an additional learned drift term that lowers the impact of the unbiasing weights used in AIS. We show that this drift is the minimizer of a variety of objective functions, which can all be estimated in an unbiased fashion without backpropagating through solutions of the stochastic differential equations governing the sampling. We also prove that some these objectives control the Kullback-Leibler divergence of the estimated distribution from its target. NETS is shown to be unbiased and, in addition, has a tunable diffusion coefficient which can be adjusted post-training to maximize the effective sample size. We demonstrate the efficacy of the method on standard benchmarks, high-dimensional Gaussian mixture distributions, and a model from statistical lattice field theory, for which it surpasses the performances of related work and existing baselines.

Key facts. Cited by 69 papers in the map (data through 14 Oct 2026). Builds on 25 of its 44 references that are in the map. First posted on arXiv 3 Oct 2024.

Builds on

25 of 44 references.

References · 25

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 2022Flow Matching for Generative Modelingcited by 5,702
  4. 2018Neural Ordinary Differential Equationscited by 3,779
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  6. 2022Building Normalizing Flows with Stochastic Interpolantscited by 995
  7. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 939
  8. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modelingcited by 602
  9. 2021Path Integral Sampler: a stochastic control approach for samplingcited by 181
  10. 2023Denoising Diffusion Samplerscited by 149
  11. 2019Flow-based generative models for Markov chain Monte Carlo in lattice field theorycited by 148
  12. 2022An optimal control perspective on diffusion-based generative modelingcited by 147
13 more
  1. 2022Flow Annealed Importance Sampling Bootstrapcited by 127
  2. 2024Iterated Denoising Energy Matching for Sampling from Boltzmann Densitiescited by 116
  3. 2022Action Matching: Learning Stochastic Dynamics from Samplescited by 98
  4. 2021Annealed Flow Transport Monte Carlocited by 90
  5. 2022Continual Repeated Annealed Flow Transport Monte Carlocited by 66
  6. 2024Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Samplingcited by 56
  7. 2024Improved off-policy training of diffusion samplerscited by 48
  8. 2023Learning Interpolations between Boltzmann Densitiescited by 43
  9. 2022Stochastic normalizing flows as non-equilibrium transformationscited by 25
  10. 2024Liouville Flow Importance Samplercited by 25
  11. 2022A Unified Perspective on Natural Gradient Variational Inference with Gaussian Mixture Modelscited by 22
  12. 2024Posterior Sampling with Denoising Oracles via Tilted Transportcited by 12
  13. 2024Harmonic Path Integral Diffusioncited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 39; 2026: 26.

69 papers.

Sort:

By area:

  1. 2025Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Expertscited by 96
  2. 2025Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matchingcited by 85
  3. 2024Sequential Controlled Langevin Diffusionscited by 48
  4. 2025Scalable Equilibrium Sampling with Sequential Boltzmann Generatorscited by 38
  5. 2025Debiasing Guidance for Discrete Diffusion with Sequential Monte Carlocited by 31
  6. 2025LEAPS: A discrete neural sampler via locally equivariant networkscited by 31
  7. 2025No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplerscited by 28
  8. 2025Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densitiescited by 26
  9. 2025Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Modelscited by 23
  10. 2025Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inferencecited by 23
  11. 2025DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion Modelscited by 23
  12. 2025Tilt Matching for Scalable Sampling and Fine-Tuningcited by 22
38 more
  1. 2024Training Neural Samplers with Reverse Diffusive KL Divergencecited by 21
  2. 2025Adjoint Schr"odinger Bridge Samplercited by 21
  3. 2025MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Controlcited by 21
  4. 2025Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approachcited by 18
  5. 2025Accelerated Parallel Tempering via Neural Transportscited by 17
  6. 2025RNE: plug-and-play diffusion inference-time control and energy-based trainingcited by 17
  7. 2025FEAT: Free energy Estimators with Adaptive Transportcited by 16
  8. 2025Proximal Diffusion Neural Samplercited by 16
  9. 2025Value Gradient Guidance for Flow Matching Alignmentcited by 14
  10. 2025Progressive Tempering Sampler with Diffusioncited by 13
  11. 2025Amortized Sampling with Transferable Normalizing Flowscited by 12
  12. 2025Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyondcited by 11
  13. 2024Scaling of Stochastic Normalizing Flows in SU(3) lattice gauge theorycited by 10
  14. 2025On scalable and efficient training of diffusion samplerscited by 10
  15. 2025Learning Boltzmann Generators via Constrained Mass Transportcited by 9
  16. 2025Non-equilibrium Annealed Adjoint Samplercited by 8
  17. 2025Energy-Weighted Flow Matching: Unlocking Continuous Normalizing Flows for Efficient and Scalable Boltzmann Samplingcited by 7
  18. 2025Iterative Importance Fine-tuning of Diffusion Modelscited by 6
  19. 2025Data-to-Energy Stochastic Dynamicscited by 6
  20. 2025Reinforced sequential Monte Carlo for amortised samplingcited by 6
  21. 2025Scaling flow-based approaches for topology sampling in SU(3) gauge theorycited by 6
  22. 2025Neural Flow Samplers with Shortcut Modelscited by 5
  23. 2025Sequential Monte Carlo approximations of Wasserstein--Fisher--Rao gradient flowscited by 5
  24. 2025HollowFlow: Efficient Sample Likelihood Evaluation using Hollow Message Passingcited by 5
  25. 2026Flow Sampling: Learning to Sample from Unnormalized Densities via Denoising Conditional Processescited by 5
  26. 2026Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusioncited by 5
  27. 2026Discrete Adjoint Schr"odinger Bridge Samplercited by 4
  28. 2024An Efficient On-Policy Deep Learning Framework for Stochastic Optimal Controlcited by 3
  29. 2025Energy-based generator matching: A neural sampler for general state spacecited by 3
  30. 2025Assessing generative modeling approaches for free energy estimates in condensed mattercited by 3
  31. 2026SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogatecited by 3
  32. 2025Importance Weighted Score Matching for Diffusion Samplers with Enhanced Mode Coveragecited by 2
  33. 2026Euphonium: Steering Video Flow Matching via Process Reward Gradient Guided Stochastic Dynamicscited by 2
  34. 2026Discrete diffusion samplers and bridges: Off-policy algorithms and applications in latent spacescited by 2
  35. 2026A unified perspective on fine-tuning and sampling with diffusion and flow modelscited by 2
  36. 2026Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measurescited by 2
  37. 2025Continuously Tempered Diffusion Samplerscited by 1
  38. 2026Counterdiabatic Hamiltonian Monte Carlocited by 1

50 most cited of 69 All 69 (JSON)