paper-with-me

홈 › Papers

Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective

2024-05-26 · YIngyu Liang, Zhenmei Shi, Zhao Song, Yufa Zhou

Diffusion models have made rapid progress in generating high-quality samples across various domains. However, a theoretical understanding of the Lipschitz continuity and second momentum properties of the diffusion process is still lacking. In this paper, we bridge this gap by providing a detailed examination of these smoothness properties for the case where the target data distribution is a mixture of Gaussians, which serves as a universal approximator for smooth densities such as image data. We prove that if the target distribution is a $k$-mixture of Gaussians, the density of the entire diffusion process will also be a $k$-mixture of Gaussians. We then derive tight upper bounds on the Lipschitz constant and second momentum that are independent of the number of mixture components $k$. Finally, we apply our analysis to various diffusion solvers, both SDE and ODE based, to establish concrete error guarantees in terms of the total variation distance and KL divergence between the target and learned distributions. Our results provide deeper theoretical insights into the dynamics of the diffusion process under common data distributions.

📄 PDF Abstract BibTeX arXiv:2405.16418

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Product-of-Gaussian-Mixture Diffusion Models for Joint Nonlinear MRI Reconstruction

2026-05-11 · Laurenz Nagler, Martin Zach, Thomas Pock arxiv

Recently, diffusion models have attracted considerable attention for magnetic resonance image reconstruction due to their high sample quality. However, most existing methods rely on large networks with opaque time-condit…

Image ReconstructionMRI Reconstruction

Networks of Causal Abstractions: A Sheaf-theoretic Framework

2025-09-25 · Gabriele D'Acunto, Paolo Di Lorenzo, Sergio Barbarossa arxiv

A core challenge in causal artificial intelligence is the principled coordination of multiple, imperfect, and subjective causal perspectives arising from distributed agents with limited and heterogeneous access to the en…

Portfolio Optimization

Product of Gaussian Mixture Diffusion Model for non-linear MRI Inversion

2025-01-15 · Laurenz Nagler, Martin Zach, Thomas Pock

Diffusion models have recently shown remarkable results in magnetic resonance imaging reconstruction. However, the employed networks typically are black-box estimators of the (smoothed) prior score with tens of millions …

Learning Mixtures of Smooth Product Distributions: Identifiability and Algorithm

2019-04-02 · Nikos Kargas, Nicholas D. Sidiropoulos

We study the problem of learning a mixture model of non-parametric product distributions. The problem of learning a mixture model is that of finding the component distributions along with the mixing weights using observe…

On the Identifiability and Interpretability of Gaussian Process Models

2023-09-21 · NeurIPS 2023 11

In this paper, we critically examine the prevalent practice of using additive mixtures of Mat\'ern kernels in single-output Gaussian process (GP) models and explore the properties of multiplicative mixtures of Mat\'ern k…