A solvable generative model with a linear, one-step denoiser
We develop an analytically tractable single-step diffusion model based on a linear denoiser and present explicit formula for the Kullback-Leibler divergence between generated and sampling distribution, taken to be isotropic Gaussian, showing the effect of finite diffusion time and noise scale. Our study further reveals that the monotonic fall phase of Kullback-Leibler divergence begins when the training dataset size reaches the dimension of the data points. Along the way, we provide a mathematically precise definition of memorization to non-memorization transition when only finite number of data points are available. It is shown that the simplified model also features this transition during the monotonic fall phase of the aforementioned Kullback-Leibler divergence. For large-scale practical diffusion models, we explain why higher number of diffusion steps enhance production quality based on the theoretical arguments presented before. In addition, we show that higher diffusion steps does not necessarily help in reducing memorization. These two facts combined suggests existence of an optimal number of diffusion steps for finite number of training samples.
Code (0)
등록된 구현이 없습니다.
Tasks
MemorizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs
The covariance for clean data given a noisy observation is an important quantity in many conditional generation methods for diffusion models. Current methods require heavy test-time computation, altering the standard dif…
Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework
While score-based generative models have emerged as powerful priors for solving inverse problems, directly integrating them into optimization algorithms such as ADMM remains nontrivial. Two central challenges arise: i) t…
Filtered Iterative Denoising for Linear Inverse Problems
Iterative denoising algorithms (IDAs) have been tremendously successful in a range of linear inverse problems arising in signal and image processing. The classic instance of this is the famous Iterative Soft-Thresholding…
DenoisingMixed Graph Signal Analysis of Joint Image Denoising / Interpolation
A noise-corrupted image often requires interpolation. Given a linear denoiser and a linear interpolator, when should the operations be independently executed in separate steps, and when should they be combined and jointl…
DenoisingImage DenoisingLinearized ADMM and Fast Nonlocal Denoising for Efficient Plug-and-Play Restoration
In plug-and-play image restoration, the regularization is performed using powerful denoisers such as nonlocal means (NLM) or BM3D. This is done within the framework of alternating direction method of multipliers (ADMM), …
DenoisingImage RestorationSuper-Resolution