paper-with-me

홈 › Papers

Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions

2024-09-27 · Iskander Azangulov, George Deligiannidis, Judith Rousseau

Denoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions and are widely used for image, audio, and video generation as well as many more applications in science and beyond. The \textit{manifold hypothesis} states that high-dimensional data often lie on lower-dimensional manifolds within the ambient space, and is widely believed to hold in provided examples. While recent results have provided invaluable insight into how diffusion models adapt to the manifold hypothesis, they do not capture the great empirical success of these models, making this a very fruitful research direction. In this work, we study DDPMs under the manifold hypothesis and prove that they achieve rates independent of the ambient dimension in terms of score learning. In terms of sampling complexity, we obtain rates independent of the ambient dimension w.r.t. the Kullback-Leibler divergence, and $O(\sqrt{D})$ w.r.t. the Wasserstein distance. We do this by developing a new framework connecting diffusion models to the well-studied theory of extrema of Gaussian Processes.

📄 PDF Abstract BibTeX arXiv:2409.18804

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingGaussian ProcessesVideo Generation

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

Linear Convergence of Diffusion Models Under the Manifold Hypothesis

2024-10-11 · Peter Potaptchik, Iskander Azangulov, George Deligiannidis

Score-matching generative models have proven successful at sampling from complex high-dimensional data distributions. In many applications, this distribution is believed to concentrate on a much lower $d$-dimensional man…

Convergence of denoising diffusion models under the manifold hypothesis

2022-08-10 · Valentin De Bortoli

Denoising diffusion models are a recent class of generative models exhibiting state-of-the-art performance in image and audio synthesis. Such models approximate the time-reversal of a forward noising process from a targe…

Audio SynthesisDenoising

Interpreting and Improving Diffusion Models from an Optimization Perspective

2023-06-08 · Frank Permenter, Chenyang Yuan

Denoising is intuitively related to projection. Indeed, under the manifold hypothesis, adding random noise is approximately equivalent to orthogonal perturbation. Hence, learning to denoise is approximately learning to p…

Denoising

Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive

2025-10-02 · Tyler Farghly, Peter Potaptchik, Samuel Howard, George Deligiannidis 외 arxiv

Diffusion models have achieved state-of-the-art performance, demonstrating remarkable generalisation capabilities across diverse domains. However, the mechanisms underpinning these strong capabilities remain only partial…

Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connections

2024-04-03 · Gabriel Loaiza-Ganem, Brendan Leigh Ross, Rasa Hosseinzadeh, Anthony L. Caterini 외

In recent years there has been increased interest in understanding the interplay between deep generative models (DGMs) and the manifold hypothesis. Research in this area focuses on understanding the reasons why commonly-…