中文
相关论文

相关论文: Optimizing Input of Denoising Score Matching is Bi…

200 篇论文

Denoising Score Matching estimates the score of a noised version of a target distribution by minimizing a regression loss and is widely used to train the popular class of Denoising Diffusion Models. A well known limitation of Denoising…

机器学习 · 计算机科学 2024-02-14 Valentin De Bortoli , Michael Hutchinson , Peter Wirnsberger , Arnaud Doucet

We theoretically investigate the phenomena of generalization and memorization in diffusion models. Empirical studies suggest that these phenomena are influenced by model complexity and the size of the training dataset. In our experiments,…

机器学习 · 计算机科学 2025-10-09 Anand Jerry George , Rodrigo Veiga , Nicolas Macris

Denoising score matching plays a pivotal role in the performance of diffusion-based generative models. However, the empirical optimal score--the exact solution to the denoising score matching--leads to memorization, where generated samples…

机器学习 · 统计学 2025-05-07 Yu-Han Wu , Pierre Marion , Gérard Biau , Claire Boyer

Diffusion models are typically trained using score matching, a learning objective agnostic to the underlying noising process that guides the model. This paper argues that Markov noising processes enjoy an advantage over alternatives, as the…

机器学习 · 统计学 2025-05-27 Zheyang Shen , Huihui Wang , Marina Riabiz , Chris J. Oates

Denoising diffusions are state-of-the-art generative models exhibiting remarkable empirical performance. They work by diffusing the data distribution into a Gaussian distribution and then learning to reverse this noising process to obtain…

机器学习 · 统计学 2024-02-20 Joe Benton , Yuyang Shi , Valentin De Bortoli , George Deligiannidis , Arnaud Doucet

Reversing a diffusion process by learning its score forms the heart of diffusion-based generative modeling and for estimating properties of scientific systems. The diffusion processes that are tractable center on linear processes with a…

机器学习 · 计算机科学 2024-07-12 Raghav Singhal , Mark Goldstein , Rajesh Ranganath

Diffusion models have achieved remarkable success in generative modeling. However, this study confirms the existence of overfitting in diffusion model training, particularly in data-limited regimes. To address this challenge, we propose…

机器学习 · 计算机科学 2025-08-12 Liang Hou , Yuan Gao , Boyuan Jiang , Xin Tao , Qi Yan , Renjie Liao , Pengfei Wan , Di Zhang , Kun Gai

How diffusion models generalize beyond their training set is not known, and is somewhat mysterious given two facts: the optimum of the denoising score matching (DSM) objective usually used to train diffusion models is the score function of…

机器学习 · 计算机科学 2025-04-18 John J. Vastola

We investigate the approximation efficiency of score functions by deep neural networks in diffusion-based generative modeling. While existing approximation theories utilize the smoothness of score functions, they suffer from the curse of…

机器学习 · 计算机科学 2023-09-21 Song Mei , Yuchen Wu

The success of denoising diffusion models raises important questions regarding their generalisation behaviour, particularly in high-dimensional settings. Notably, it has been shown that when training and sampling are performed perfectly,…

机器学习 · 统计学 2025-07-08 Tyler Farghly , Patrick Rebeschini , George Deligiannidis , Arnaud Doucet

Score matching enables the estimation of the gradient of a data distribution, a key component in denoising diffusion models used to recover clean data from corrupted inputs. In prior work, a heuristic weighting function has been used for…

机器学习 · 计算机科学 2025-08-05 Juyan Zhang , Rhys Newbury , Xinyang Zhang , Tin Tran , Dana Kulic , Michael Burke

We study the theoretical behavior of denoising score matching--the learning task associated to diffusion models--when the data distribution is supported on a low-dimensional manifold and the score is parameterized using a random feature…

机器学习 · 计算机科学 2026-04-14 Anand Jerry George , Nicolas Macris

Diffusion models are gaining widespread use in cutting-edge image, video, and audio generation. Score-based diffusion models stand out among these methods, necessitating the estimation of score function of the input data distribution. In…

机器学习 · 计算机科学 2024-05-24 Fangzhao Zhang , Mert Pilanci

Diffusion models have become a leading paradigm in generative AI, with score estimation via denoising score matching as a central component. While recent theory provides strong statistical guarantees, it typically relies on…

机器学习 · 计算机科学 2026-04-21 Yinbin Han , Meisam Razaviyayn , Renyuan Xu

The density estimation is one of the core problems in statistics. Despite this, existing techniques like maximum likelihood estimation are computationally inefficient due to the intractability of the normalizing constant. For this reason an…

机器学习 · 计算机科学 2021-01-14 Tsimboy Olga , Yermek Kapushev , Evgeny Burnaev , Ivan Oseledets

Most existing theoretical investigations of the accuracy of diffusion models, albeit significant, assume the score function has been approximated to a certain accuracy, and then use this a priori bound to control the error of generation.…

机器学习 · 计算机科学 2024-10-29 Yuqing Wang , Ye He , Molei Tao

The denoising diffusion model has recently emerged as a powerful generative technique, capable of transforming noise into meaningful data. While theoretical convergence guarantees for diffusion models are well established when the target…

机器学习 · 计算机科学 2025-03-28 Yuchen Liang , Peizhong Ju , Yingbin Liang , Ness Shroff

Discrete-time diffusion-based generative models and score matching methods have shown promising results in modeling high-dimensional image data. Recently, Song et al. (2021) show that diffusion processes that transform data into noise can…

机器学习 · 计算机科学 2021-10-01 Chin-Wei Huang , Jae Hyun Lim , Aaron Courville

Deep neural networks (DNNs) trained for image denoising are able to generate high-quality samples with score-based reverse diffusion algorithms. These impressive capabilities seem to imply an escape from the curse of dimensionality, but…

计算机视觉与模式识别 · 计算机科学 2025-03-03 Zahra Kadkhodaie , Florentin Guth , Eero P. Simoncelli , Stéphane Mallat

Diffusion-based methods represented as stochastic differential equations on a continuous-time domain have recently proven successful as a non-adversarial generative model. Training such models relies on denoising score matching, which can…

机器学习 · 计算机科学 2024-11-05 Sarthak Mittal , Korbinian Abstreiter , Stefan Bauer , Bernhard Schölkopf , Arash Mehrjou
‹ 上一页 1 2 3 10 下一页 ›