Accelerated diffusion models hold the potential to significantly enhance the efficiency of standard diffusion processes. Theoretically, these models have been shown to achieve faster convergence rates than the standard $\mathcal O(1/ε^2)$ rate of vanilla diffusion models, where $ε$ denotes the target accuracy. However, current theoretical studies have established the acceleration advantage only for restrictive target distribution classes, such as those with smoothness conditions imposed along the entire sampling path or with bounded support. In this work, we significantly broaden the target distribution classes with a new accelerated stochastic DDPM sampler. In particular, we show that it achieves accelerated performance for three broad distribution classes not considered before. Our first class relies on the smoothness condition posed only to the target density $q_0$, which is far more relaxed than the existing smoothness conditions posed to all $q_t$ along the entire sampling path. Our second class requires only a finite second moment condition, allowing for a much wider class of target distributions than the existing finite-support condition. Our third class is Gaussian mixture, for which our result establishes the first acceleration guarantee. Moreover, among accelerated DDPM type samplers, our results specialized for bounded-support distributions show an improved dependency on the data dimension $d$. Our analysis introduces a novel technique for establishing performance guarantees via constructing a tilting factor representation of the convergence error and utilizing Tweedie's formula to handle Taylor expansion terms. This new analytical framework may be of independent interest.
Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation
Shanghai Academy of Artificial Intelligence for Science, SAIS(上海人工智能科学研究院,SAIS);College of Chemistry and Chemical Engineering, Xiamen University(厦门大学化学与化工学院);Artificial Intelligence Innovation and Incubation (AI 3 ) Institute, Fudan University(复旦大学人工智能创新与孵化(AI 3)研究院)
High-Frequency Space Diffusion Models for Accelerated MRI
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);University of Chinese Academy of Sciences(中国科学院大学);Shenzhen University(深圳大学);Pazhou Lab(琶洲实验室)
Accelerated, physics-inspired inference of skeletal muscle microstructure from diffusion-weighted MRI
Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校贝克曼高级科学技术研究所);Illinois Institute of Technology(伊利诺伊理工学院)
DiffusionLight-Turbo: Accelerated Light Probes for Free via Single-Pass Chrome Ball Inpainting
Tokyo Institute of Technology(东京技术大学);Siam Commercial Bank(暹罗商业银行);School of Information Science and Technology, VISTEC(信息科学与技术学院,VISTEC);Google DeepMind(谷歌DeepMind)
Accelerating Stroke MRI with Diffusion Probabilistic Models through Large-Scale Pre-training and Target-Specific Fine-Tuning
Chandra Family Department of Electrical and Computer Engineering(查克拉家族电气与计算机工程系);Department of Imaging Physics(成像物理系);Dell Medical School Department of Neurology(德莱尔医学院神经学系);Dell Medical School Department of Neurosurgery(德莱尔医学院神经外科系);Dell Medical School Department of Diagnostic Medicine(德莱尔医学院诊断医学系);Oden Institute for Computational Engineering and Sciences(奥登计算工程与科学研究院)
Deep Operator Networks~(DeepONet)是一种完全不同的神经网络,我们训练它来近似非线性算子,包括参数偏微分方程(PDE)的求解算子。DeepONets已经显示出卓越的近似和泛化能力,即使在使用相对较小的数据集进行训练时也是如此。然而,当训练数据被噪声污染时,DeepONets的性能会恶化,这种情况在实践中经常发生。为了使DeepONets能够使用噪声数据进行训练,我们建议使用复制交换Langevin扩散的贝叶斯框架。这样的框架使用两个粒子,一个用于探索,另一个用于利用DeepONets的损失函数。我们表明,所提出的框架的探索和利用能力使(1)在嘈杂的场景中提高DeepONets的训练收敛性,以及(2)为参数PDE的预测解附加不确定性估计。此外,我们还发现,与使用最先进的基于梯度的优化算法(例如Adam)训练的香草DeepONets相比,复制交换Langeving扩散(显着)还提高了DeepONet在嘈杂场景中的平均预测准确性。为了降低副本的潜在高计算成本,在这项工作中,我们提出了一个用于复制交换Langevin扩散的加速训练框架,该框架利用DeepONets的神经网络架构将其计算成本降低了25%,而不会影响所提出的框架的性能。最后,我们使用一系列的实验四个参数偏微分方程的问题,说明了所提出的贝叶斯框架的有效性。
Chandra Family Department of Electrical and Computer Engineering The University of Texas at Austin(电气与计算机工程系Chandra家族部门德克萨斯大学奥斯汀分校);Department of Imaging Physics MD Anderson Cancer Center(成像物理系MD安德森癌症中心);Department of Diagnostic Medicine The University of Texas at Austin Dell Medical School(诊断医学系德克萨斯大学奥斯汀分校Dell医学院);Oden Institute for Computational Engineering and Sciences The University of Texas at Austin(计算工程与科学学院Oden研究所德克萨斯大学奥斯汀分校)