Statistical guarantees for denoising reflected diffusion models

Дата публикации: 17-08-2026 20:26:00

In recent years, denoising diffusion models have become a crucial area of research due to their abundance in the rapidly expanding field of generative AI. While recent statistical advances have delivered explanations for the generation ability of idealised denoising diffusion models for high-dimensional target data, implementations introduce thresholding procedures for the generating process to overcome issues arising from the unbounded state space of such models. This mismatch between theoretical design and implementation of diffusion models has been addressed empirically by using a reflected diffusion process as the driver of noise instead. In this paper, we study statistical guarantees of these denoising reflected diffusion models. In particular, under Sobolev smoothness assumptions, we establish rates of convergence in total variation which, up to a polylogarithmic factor, match the minimax lower bound. Our main contributions include the statistical analysis of this novel class of denoising reflected diffusion models and a refined score approximation method in both time and space, leveraging spectral decomposition and rigorous neural network analysis.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	Nonparametric Estimation of a Factorizable Density using Diffusion Models	0	8.59	17-08-2026
2	A Unified Approach to Analysis and Design of Denoising Markov Models	0	6.14	17-08-2026
3	Error Analysis for Deep ReLU Feedforward Density-Ratio Estimation with Bregman Divergence	0	8.78	17-08-2026
4	Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent	0	6.66	17-08-2026
5	Statistical Learning Theory for Neural Operators	0	10.21	17-08-2026
6	High-Dimensional Analysis of Gradient Flow for Extensive-Width Quadratic Neural Networks	0	8.7	17-08-2026
7	Nonlocal Techniques for the Analysis of Deep ReLU Neural Network Approximations	0	6.62	17-08-2026
8	Nonparametric generative modeling for time series via Schr{\"{o}}dinger bridge	0	5.53	17-08-2026
9	Convergence of Noise-Free Sampling Algorithms with Regularized Wasserstein Proximals	0	8.02	17-08-2026
10	Minimax density estimation in the adversarial framework under local differential privacy	0	3.48	17-08-2026

Классификация: Пресс-релизы. Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 5.3. Источник: jmlr.org.