mlsanityData to 7 Oct 2026

Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization

arXiv 2310.02679 ↗First posted 4 Oct 2023cs.LG cs.AI stat.COcited by 57

Not on the map. Why?

Cited by 26 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We tackle the problem of sampling from intractable high-dimensional density functions, a fundamental task that often appears in machine learning and statistics. We extend recent sampling-based approaches that leverage controlled stochastic processes to model approximate samples from these target densities. The main drawback of these approaches is that the training objective requires full trajectories to compute, resulting in sluggish credit assignment issues due to use of entire trajectories and a learning signal present only at the terminal time. In this work, we present Diffusion Generative Flow Samplers (DGFS), a sampling-based framework where the learning process can be tractably broken down into short partial trajectory segments, via parameterizing an additional "flow function". Our method takes inspiration from the theory developed for generative flow networks (GFlowNets), allowing us to make use of intermediate learning signals. Through various challenging experiments, we demonstrate that DGFS achieves more accurate estimates of the normalization constant than closely-related prior methods.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 67 of its 104 references that are in the map. First posted on arXiv 4 Oct 2023.

Builds on

67 of 104 references.

References · 67

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2018Neural Ordinary Differential Equationscited by 3,733
  5. 2015Variational Inference with Normalizing Flowscited by 2,161
  6. 2016Variational Inference: A Review for Statisticianscited by 1,466
  7. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  8. 2015Importance Weighted Autoencoderscited by 454
  9. 2022Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptionscited by 440
  10. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  11. 2014Stochastic Gradient Hamiltonian Monte Carlocited by 341
  12. 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
38 more
  1. 2021GFlowNet Foundationscited by 286
  2. 2022Convergence of denoising diffusion models under the manifold hypothesiscited by 237
  3. 2022Convergence of score-based generative modeling for general data distributionscited by 179
  4. 2021Path Integral Sampler: a stochastic control approach for samplingcited by 175
  5. 2013Expectation Propagation for approximate Bayesian inferencecited by 172
  6. 2022Biological Sequence Design with GFlowNetscited by 172
  7. 2020Stochastic Normalizing Flowscited by 156
  8. 2018Neural Importance Samplingcited by 154
  9. 2022Bayesian Structure Learning with Generative Flow Networkscited by 153
  10. 2019Flow-based generative models for Markov chain Monte Carlo in lattice field theorycited by 147
  11. 2022An optimal control perspective on diffusion-based generative modelingcited by 145
  12. 2023Denoising Diffusion Samplerscited by 144
  13. 2022Learning GFlowNets from partial episodes for improved convergence and stabilitycited by 129
  14. 2022Flow Annealed Importance Sampling Bootstrapcited by 124
  15. 2022Generative Flow Networks for Discrete Probabilistic Modelingcited by 113
  16. 2022GFlowNets and variational inferencecited by 103
  17. 2023Improved sampling via learned diffusionscited by 103
  18. 2022Multi-Objective GFlowNetscited by 100
  19. 2018Solving Statistical Mechanics Using Variational Autoregressive Networkscited by 99
  20. 2023A theory of continuous generative flow networkscited by 98
  21. 2017Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inferencecited by 97
  22. 2019Theoretical guarantees for sampling and inference in generative models with latent diffusionscited by 97
  23. 2021Annealed Flow Transport Monte Carlocited by 90
  24. 2023Better Training of GFlowNets with Local Credit and Incomplete Trajectoriescited by 83
  25. 2023Towards Understanding and Improving GFlowNet Trainingcited by 74
  26. 2020Neural Approximate Sufficient Statistics for Implicit Modelscited by 72
  27. 2023Robust Scheduling with GFlowNetscited by 67
  28. 2020Targeted free energy estimation via learned mappingscited by 66
  29. 2022Continual Repeated Annealed Flow Transport Monte Carlocited by 66
  30. 2023GFlowNets for AI-Driven Scientific Discoverycited by 63
  31. 2021Bayesian Learning via Neural Schr"odinger-F"ollmer Flowscited by 56
  32. 2022Score-Based Diffusion meets Annealed Importance Samplingcited by 51
  33. 2023Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Networkcited by 50
  34. 2022Generative Augmented Flow Networkscited by 48
  35. 2023GFlowNet-EM for learning compositional latent variable modelscited by 40
  36. 2023Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNetscited by 40
  37. 2022A Variational Perspective on Generative Flow Networkscited by 39
  38. 2021Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equationscited by 38

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 24; 2025: 24; 2026: 9.

57 papers.

Sort:

By area:

  1. 2024Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Controlcited by 136
  2. 2025Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matchingcited by 78
  3. 2024Amortizing intractable inference in diffusion models for vision, language, and controlcited by 70
  4. 2024Particle Denoising Diffusion Samplercited by 63
  5. 2024Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Samplingcited by 55
  6. 2025DIME:Diffusion-Based Maximum Entropy Reinforcement Learningcited by 52
  7. 2024Improved off-policy training of diffusion samplerscited by 47
  8. 2024Sequential Controlled Langevin Diffusionscited by 47
  9. 2024Target Score Matchingcited by 46
  10. 2024DEFT: Efficient Fine-Tuning of Diffusion Models by Learning the Generalised h-transformcited by 44
  11. 2025FlowRL: Matching Reward Distributions for LLM Reasoningcited by 38
  12. 2024Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNetscited by 30
38 more
  1. 2025Underdamped Diffusion Bridges with Applications to Samplingcited by 28
  2. 2024Sampling in Unit Time with Kernel Fisher-Rao Flowcited by 27
  3. 2024Improving GFlowNets for Text-to-Image Diffusion Alignmentcited by 27
  4. 2025No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplerscited by 25
  5. 2024Adaptive teachers for amortized samplerscited by 23
  6. 2025Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inferencecited by 22
  7. 2024Training Neural Samplers with Reverse Diffusive KL Divergencecited by 21
  8. 2024Dynamical Measure Transport and Neural PDE Solvers for Samplingcited by 19
  9. 2025From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster trainingcited by 17
  10. 2025Temperature-Annealed Boltzmann Generatorscited by 14
  11. 2025Generative Models in Decision Making: A Surveycited by 14
  12. 2025Value Gradient Guidance for Flow Matching Alignmentcited by 14
  13. 2024Pessimistic Backward Policy for GFlowNetscited by 13
  14. 2025Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewardscited by 11
  15. 2025On scalable and efficient training of diffusion samplerscited by 10
  16. 2024Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flowscited by 9
  17. 2024Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networkscited by 9
  18. 2024Baking Symmetry into GFlowNetscited by 7
  19. 2026Bridge Matching Sampler: Scalable Sampling via Generalized Fixed-Point Diffusion Matchingcited by 7
  20. 2024On Divergence Measures for Training GFlowNetscited by 6
  21. 2025Adaptive Destruction Processes for Diffusion Samplerscited by 6
  22. 2025Neural Flow Samplers with Shortcut Modelscited by 5
  23. 2025Reinforced sequential Monte Carlo for amortised samplingcited by 5
  24. 2024Ada-HGNN: Adaptive Sampling for Scalable Hypergraph Neural Networkscited by 4
  25. 2025End-To-End Learning of Gaussian Mixture Priors for Diffusion Samplercited by 4
  26. 2025AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusioncited by 4
  27. 2025Posterior Inference in Latent Space for Scalable Constrained Black-box Optimizationcited by 4
  28. 2026TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignmentcited by 4
  29. 2026A Minimum Variance Path Principle for Accurate and Stable Score-Based Density Ratio Estimationcited by 3
  30. 2024Denoising Diffusion Variational Inference: Diffusion Models as Expressive Variational Posteriorscited by 2
  31. 2024HJ-sampler: A Bayesian sampler for inverse problems of a stochastic process by leveraging Hamilton-Jacobi PDEs and score-based generative modelscited by 2
  32. 2025Importance Weighted Score Matching for Diffusion Samplers with Enhanced Mode Coveragecited by 2
  33. 2025One-Step Diffusion Samplers via Self-Distillation and Deterministic Flowcited by 1
  34. 2026Onsager-Machlup Posterior Transport for Deep Gaussian Processescited by 1
  35. 2024Dynamic Backtracking in GFlowNets: Enhancing Decision Steps with Reward-Dependent Adjustment Mechanismscited by 0
  36. 2024Flow Perturbation to Accelerate Unbiased Sampling of Boltzmann distributioncited by 0
  37. 2025Single-Step Consistent Diffusion Samplerscited by 0
  38. 2025Value Gradient Sampler: Learning Invariant Value Functions for Equivariant Diffusion Samplingcited by 0

50 most cited of 57 All 57 (JSON)