[2604.03015] Generating DDPM-based Samples from Tilted Distributions

Computer Science > Machine Learning arXiv:2604.03015 (cs) [Submitted on 3 Apr 2026] Title:Generating DDPM-based Samples from Tilted Distributions Authors:Himadri Mandal, Dhruman Gupta, Rushil Gupta, Sarvesh Ravichandran Iyer, Agniv Bandyopadhyay, Achal Bassamboo, Varun Gupta, Sandeep Juneja View a PDF of the paper titled Generating DDPM-based Samples from Tilted Distributions, by Himadri Mandal and 7 other authors View PDF HTML (experimental) 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 $\theta \in \mathbb{R}^d$. 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 $\theta$, 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. Comments: Subjects: Machine Learning (cs.LG); Probability (math.PR); Machine Learning (stat.ML) MSC classes: ...