Generating DDPM-based Samples from Tilted Distributions
- URL: http://arxiv.org/abs/2604.03015v1
- Date: Fri, 03 Apr 2026 13:00:11 GMT
- Title: Generating DDPM-based Samples from Tilted Distributions
- Abstract summary: 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.<n>We define a plug-in estimator and show that it is minimax-optimal.<n>Our theoretical results are supported by extensive simulations.
- Score: 17.60723761100761
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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 $θ\in \mathbb{R}^d$. 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.
Related papers
- Fundamental limits for weighted empirical approximations of tilted distributions [3.172282943656995]
Consider the task of generating samples from a tilted distribution of a random vector whose underlying distribution is unknown, but samples from it are available.<n>This finds applications in fields such as finance and climate science, and in rare event simulation.<n>We provide a sharp characterization of its accuracy, given the number of samples and the degree of tilt.
arXiv Detail & Related papers (2025-12-30T04:30:27Z) - Minimax Optimality of the Probability Flow ODE for Diffusion Models [8.15094483029656]
This work develops the first end-to-end theoretical framework for deterministic ODE-based samplers.<n>We propose a smooth regularized score estimator that simultaneously controls both the $L2$ score error and the associated mean Jacobian error.<n>We demonstrate that the resulting sampler achieves the minimax rate in total variation distance, modulo logarithmic factors.
arXiv Detail & Related papers (2025-03-12T17:51:29Z) - Enhanced Importance Sampling through Latent Space Exploration in Normalizing Flows [69.8873421870522]
importance sampling is a rare event simulation technique used in Monte Carlo simulations.<n>We propose a method for more efficient sampling by updating the proposal distribution in the latent space of a normalizing flow.
arXiv Detail & Related papers (2025-01-06T21:18:02Z) - Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
We present the first performance guarantee with explicit dimensional dependencies for general score-mismatched diffusion samplers.<n>We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions.<n>This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
arXiv Detail & Related papers (2024-10-17T16:42:12Z) - Non-asymptotic bounds for forward processes in denoising diffusions: Ornstein-Uhlenbeck is hard to beat [49.1574468325115]
This paper presents explicit non-asymptotic bounds on the forward diffusion error in total variation (TV)<n>We parametrise multi-modal data distributions in terms of the distance $R$ to their furthest modes and consider forward diffusions with additive and multiplicative noise.
arXiv Detail & Related papers (2024-08-25T10:28:31Z) - A Sharp Convergence Theory for The Probability Flow ODEs of Diffusion Models [45.60426164657739]
We develop non-asymptotic convergence theory for a diffusion-based sampler.
We prove that $d/varepsilon$ are sufficient to approximate the target distribution to within $varepsilon$ total-variation distance.
Our results also characterize how $ell$ score estimation errors affect the quality of the data generation processes.
arXiv Detail & Related papers (2024-08-05T09:02:24Z) - Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative
Models [49.81937966106691]
We develop a suite of non-asymptotic theory towards understanding the data generation process of diffusion models.
In contrast to prior works, our theory is developed based on an elementary yet versatile non-asymptotic approach.
arXiv Detail & Related papers (2023-06-15T16:30:08Z) - Sampling, Diffusions, and Stochastic Localization [10.871336306134395]
Diffusions are a successful technique to sample from high-dimensional expository distributions.<n>The drift of the diffusion process is typically represented as a neural network.<n>An algorithmic version of Markov localization was recently proposed in order to sample from certain statistical mechanics models.
arXiv Detail & Related papers (2023-05-18T04:01:40Z) - Unsupervised Learning of Sampling Distributions for Particle Filters [80.6716888175925]
We put forward four methods for learning sampling distributions from observed measurements.
Experiments demonstrate that learned sampling distributions exhibit better performance than designed, minimum-degeneracy sampling distributions.
arXiv Detail & Related papers (2023-02-02T15:50:21Z) - Unrolling Particles: Unsupervised Learning of Sampling Distributions [102.72972137287728]
Particle filtering is used to compute good nonlinear estimates of complex systems.
We show in simulations that the resulting particle filter yields good estimates in a wide range of scenarios.
arXiv Detail & Related papers (2021-10-06T16:58:34Z) - Robust Learning of Optimal Auctions [84.13356290199603]
We study the problem of learning revenue-optimal multi-bidder auctions from samples when the samples of bidders' valuations can be adversarially corrupted or drawn from distributions that are adversarially perturbed.
We propose new algorithms that can learn a mechanism whose revenue is nearly optimal simultaneously for all true distributions'' that are $alpha$-close to the original distribution in Kolmogorov-Smirnov distance.
arXiv Detail & Related papers (2021-07-13T17:37:21Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.