mlsanityData to 7 Oct 2026

Progressive Tempering Sampler with Diffusion

arXiv 2506.05231 ↗First posted 5 Jun 2025cs.LG stat.MLcited by 13

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Recent research has focused on designing neural samplers that amortize the process of sampling from unnormalized densities. However, despite significant advancements, they still fall short of the state-of-the-art MCMC approach, Parallel Tempering (PT), when it comes to the efficiency of target evaluations. On the other hand, unlike a well-trained neural sampler, PT yields only dependent samples and needs to be rerun -- at considerable computational cost -- whenever new samples are required. To address these weaknesses, we propose the Progressive Tempering Sampler with Diffusion (PTSD), which trains diffusion models sequentially across temperatures, leveraging the advantages of PT to improve the training of neural samplers. We also introduce a novel method to combine high-temperature diffusion models to generate approximate lower-temperature samples, which are minimally refined using MCMC and used to train the next diffusion model. PTSD enables efficient reuse of sample information across temperature levels while generating well-mixed, uncorrelated samples. Our method significantly improves target evaluation efficiency, outperforming diffusion-based neural samplers.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 39 of its 73 references that are in the map. First posted on arXiv 5 Jun 2025.

Builds on

39 of 73 references.

Closest ancestors · 14

Same direction, newest first

  1. 2025Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts4 Mar
  2. 2024Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs15 Oct
  3. 2024Guiding a Diffusion Model with a Bad Version of Itself4 Jun
  4. 2024Target Score Matching13 Feb
  5. 2024Particle Denoising Diffusion Sampler9 Feb
  6. 2024Improved off-policy training of diffusion samplers7 Feb
  7. 2023Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models29 May
  8. 2023Denoising Diffusion Samplers27 Feb
  9. 2023Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC22 Feb
  10. 2022Classifier-Free Diffusion Guidance26 Jul
  11. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  12. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
2 more
  1. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  2. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 25

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  4. 2018Neural Ordinary Differential Equationscited by 3,733
  5. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  6. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  7. 2021E(n) Equivariant Graph Neural Networkscited by 951
  8. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 619
  9. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 584
  10. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 248
  11. 2021Path Integral Sampler: a stochastic control approach for samplingcited by 175
  12. 2020Stochastic Normalizing Flowscited by 156
13 more
  1. 2023Equivariant flow matchingcited by 131
  2. 2022Flow Annealed Importance Sampling Bootstrapcited by 124
  3. 2024Iterated Denoising Energy Matching for Sampling from Boltzmann Densitiescited by 113
  4. 2021Annealed Flow Transport Monte Carlocited by 90
  5. 2025Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matchingcited by 78
  6. 2024NETS: A Non-Equilibrium Transport Samplercited by 67
  7. 2024Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Samplingcited by 55
  8. 2024Sequential Controlled Langevin Diffusionscited by 47
  9. 2025No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplerscited by 25
  10. 2023Transport meets Variational Inference: Controlled Monte Carlo Diffusionscited by 21
  11. 2024Diffusive Gibbs Samplingcited by 21
  12. 2024Training Neural Samplers with Reverse Diffusive KL Divergencecited by 21
  13. 2024BNEM: A Boltzmann Sampler Based on Bootstrapped Noised Energy Matchingcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 8.

13 papers.

Sort:

By area:

  1. 2025Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densitiescited by 26
  2. 2025Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inferencecited by 22
  3. 2025MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Controlcited by 20
  4. 2025CREPE: Controlling Diffusion with Replica Exchangecited by 9
  5. 2025Learning Boltzmann Generators via Constrained Mass Transportcited by 8
  6. 2026Discrete Adjoint Schr"odinger Bridge Samplercited by 4
  7. 2026Diffusion Path Samplers via Sequential Monte Carlocited by 2
  8. 2026Efficient Training of Boltzmann Generators Using Off-Policy Log-Dispersion Regularizationcited by 2
  9. 2026Discrete diffusion samplers and bridges: Off-policy algorithms and applications in latent spacescited by 2
  10. 2026Conditional Diffusion Samplingcited by 1
  11. 2026Scalable Inference-Time Annealing with Surrogate Likelihood Estimatorscited by 0
  12. 2026Mode Collapse Is Cheap to Detect: A Ground-Truth-Free Pre-Flight Check for Neural Samplerscited by 0
1 more
  1. 2026Iterative Exact Discrete Guidance for Energy-Based Samplingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Accelerated Parallel Tempering via Neural Transports
  2. 2025Continuously Tempered Diffusion Samplers
  3. 2024Diffusion-PINN Sampler
  4. 2025Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics
  5. 2025Single-Step Consistent Diffusion Samplers
  6. 2026Diversify Diffusion with Temperature Sampling and Variance-Corrective Time Shifting
  7. 2025On scalable and efficient training of diffusion samplers
  8. 2025Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow Models