Pith. sign in

REVIEW 10 cited by

Denoising Diffusion Samplers

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.13834 v2 pith:NGBXW2BW submitted 2023-02-27 cs.LG stat.ML

Francisco Vargas , Will Grathwohl , Arnaud Doucet This is my paper · ORCID
classification cs.LGstat.ML
keywords diffusiondenoisinggaussiangenerativemodelsscoredatadensity
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Denoising diffusion models are a popular class of generative models providing state-of-the-art results in many domains. One adds gradually noise to data using a diffusion to transform the data distribution into a Gaussian distribution. Samples from the generative model are then obtained by simulating an approximation of the time-reversal of this diffusion initialized by Gaussian samples. Practically, the intractable score terms appearing in the time-reversed process are approximated using score matching techniques. We explore here a similar idea to sample approximately from unnormalized probability density functions and estimate their normalizing constants. We consider a process where the target density diffuses towards a Gaussian. Denoising Diffusion Samplers (DDS) are obtained by approximating the corresponding time-reversal. While score matching is not applicable in this context, we can leverage many of the ideas introduced in generative modeling for Monte Carlo sampling. Existing theoretical results from denoising diffusion models also provide theoretical guarantees for DDS. We discuss the connections between DDS, optimal control and Schr\"odinger bridges and finally demonstrate DDS experimentally on a variety of challenging sampling tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Stochastic Quantization as Optimal Control

    hep-lat 2026-07 conditional novelty 6.0 of 10

    Stochastic quantization is re-expressed as finite-time optimal control, in which a learned Doob force plus exact path weights reach the Gibbs measure without waiting for equilibrium.

  2. Solving Inverse Problems with Flow-based Models via Model Predictive Control

    eess.IV 2026-01 conditional novelty 6.0 of 10

    MPC-Flow applies model predictive control to guide pretrained flow models through inverse problems, with a single-step variant that avoids backpropagation and scales to 32B-parameter models on consumer hardware.

  3. Path Integral Optimiser: Global Optimisation via Neural Schr\"odinger-F\"ollmer Diffusion

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A neural Schrödinger-Föllmer diffusion, trained like the Path Integral Sampler, is repurposed as a global optimizer, with new conditional convergence bounds and competitive results on small tasks only.

  4. Amortized In-Context Bayesian Posterior Estimation

    cs.LG 2025-02 conditional novelty 6.0 of 10

    A benchmark of in-context Bayesian posterior estimators shows the reverse-KL objective with transformers and normalizing flows outperforms forward-KL neural posterior estimation on predictive and out-of-distribution tasks.

  5. Debiasing Guidance for Discrete Diffusion with Sequential Monte Carlo

    cs.LG 2025-02 conditional novelty 6.0 of 10

    An SMC importance-sampling algorithm debiases discrete diffusion guidance, asymptotically sampling from the target tempered distribution p0(x0)p(ζ|x0)^α.

  6. Neural Non-Equilibrium Hamiltonian Monte Carlo for Corrected Boltzmann Sampling

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A train-then-correct Hamiltonian Monte Carlo with learned stochastic paths gives exact Boltzmann corrections via a recorded generalized work, with limited but honest empirical validation.

  7. Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning

    cs.LG 2025-12 conditional novelty 5.0 of 10

    Diffusion policies can be inserted into maximum-entropy RL by minimizing an upper bound on reverse KL, yielding DiffPPO, DiffSAC, and DiffWPO.

  8. Continuously Tempered Diffusion Samplers

    cs.LG 2025-08 conditional novelty 5.0 of 10

    CTDS trains neural samplers with a controlled Langevin dynamics over both position and a continuous temperature coordinate, and reports improved sampling on a 40-mode Gaussian mixture.

  9. Towards Adaptive External Communication in Autonomous Vehicles: A Conceptual Design Framework

    cs.HC 2025-08 unverdicted novelty 5.0 of 10

    A three-layer framework (input, processing, output) for adaptive external human-machine interfaces in autonomous vehicles is introduced to systematize design and analysis.

  10. Neural Flow Samplers with Shortcut Models

    cs.LG 2025-02 conditional novelty 5.0 of 10

    Neural Flow Shortcut Sampler (NFS2) estimates the partition-function derivative with velocity-driven SMC and Stein control variates, and adds a generalized shortcut consistency loss for few-step sampling.

Pith tools