mlsanityData to 7 Oct 2026

Generating DDPM-based Samples from Tilted Distributions

arXiv 2604.03015 ↗First posted 3 Apr 2026cs.LG math.PR stat.MLcited by 0

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Given n independent samples from a d-dimensional probability distribution, our aim is to generate diffusion-based samples from a distribution obtained by tilting the original, where the degree of tilt is parametrized by θ ∈ ℝd. We define a plug-in estimator and show that it is minimax-optimal. We develop Wasserstein bounds between the distribution of the plug-in estimator and the true distribution as a function of n and θ, illustrating regimes where the output and the desired true distribution are close. Further, under some assumptions, we prove the TV-accuracy of running Diffusion on these tilted samples. Our theoretical results are supported by extensive simulations. Applications of our work include finance, weather and climate modelling, and many other domains, where the aim may be to generate samples from a tilted distribution that satisfies practically motivated moment constraints.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 18 of its 45 references that are in the map. First posted on arXiv 3 Apr 2026.

Builds on

18 of 45 references.

Closest ancestors · 10

Same direction, newest first

  1. 2023Wasserstein Convergence Guarantees for a General Class of Score-Based Generative Models18 Nov
  2. 2023Nearly d-Linear Convergence Bounds for Diffusion Models via Stochastic Localization7 Aug
  3. 2022Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions22 Sep
  4. 2022Diffusion Models in Vision: A Survey10 Sep
  5. 2022A Survey on Generative Diffusion Model6 Sep
  6. 2022Diffusion Models: A Comprehensive Survey of Methods and Applications2 Sep
  7. 2021Variational Diffusion Models1 Jul
  8. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  9. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  10. 2020Denoising Diffusion Implicit Models6 Oct

Other references · 8

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  2. 2022Flow Matching for Generative Modelingcited by 5,426
  3. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  4. 2024Protein Conformation Generation via Force-Guided SE(3) Diffusion Modelscited by 44
  5. 2018Convergence and Concentration of Empirical Measures under Wasserstein Distance in Unbounded Functional Spacescited by 41
  6. 2024Diffusion Model-based Probabilistic Downscaling for 180-year East Asian Climate Reconstructioncited by 25
  7. 2025Robust Optimization with Diffusion Models for Green Securitycited by 4
  8. 2025Fundamental limits for weighted empirical approximations of tilted distributionscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Sublinear iterations can suffice even for DDPMs
  2. 2026Wasserstein bounds for denoising diffusion probabilistic models via the F"ollmer process
  3. 2025Minimax Optimality of the Probability Flow ODE for Diffusion Models
  4. 2023Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-Type Samplers
  5. 2026Discrete diffusion samplers and bridges: Off-policy algorithms and applications in latent spaces
  6. 2025Optimal Convergence Analysis of DDPM for General Distributions
  7. 2025Tilt Matching for Scalable Sampling and Fine-Tuning
  8. 2026Error Bounds for a Diffusion Model-Based Drift Estimator