To smooth a cloud or to pin it down: Guarantees and Insights on Score Matching in Denoising Diffusion Models
- URL: http://arxiv.org/abs/2305.09605v3
- Date: Wed, 26 Jun 2024 23:41:36 GMT
- Title: To smooth a cloud or to pin it down: Guarantees and Insights on Score Matching in Denoising Diffusion Models
- Authors: Francisco Vargas, Teodora Reu, Anna Kerekes, Michael M Bronstein,
- Abstract summary: Denoising diffusion models are a class of generative models which have recently achieved state-of-the-art results across many domains.
We leverage known connections to control akin to the F"ollmer drift to extend established neural network approximation results for the F"ollmer drift to denoising diffusion models and samplers.
- Score: 20.315727650065007
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Denoising diffusion models are a class of generative models which have recently achieved state-of-the-art results across many domains. Gradual noise is added to the data using a diffusion process, which transforms the data distribution into a Gaussian. Samples from the generative model are then obtained by simulating an approximation of the time reversal of this diffusion initialized by Gaussian samples. Recent research has explored adapting diffusion models for sampling and inference tasks. In this paper, we leverage known connections to stochastic control akin to the F\"ollmer drift to extend established neural network approximation results for the F\"ollmer drift to denoising diffusion models and samplers.
Related papers
- Continuous Diffusion Model for Language Modeling [57.396578974401734]
Existing continuous diffusion models for discrete data have limited performance compared to discrete approaches.
We propose a continuous diffusion model for language modeling that incorporates the geometry of the underlying categorical distribution.
arXiv Detail & Related papers (2025-02-17T08:54:29Z) - Generative Modeling with Bayesian Sample Inference [50.07758840675341]
We derive a novel generative model from the simple act of Gaussian posterior inference.
Treating the generated sample as an unknown variable to infer lets us formulate the sampling process in the language of Bayesian probability.
Our model uses a sequence of prediction and posterior update steps to narrow down the unknown sample from a broad initial belief.
arXiv Detail & Related papers (2025-02-11T14:27:10Z) - Generative Modeling with Diffusion [0.0]
We introduce the diffusion model as a method to generate new samples.
We will define the noising and denoising processes, then introduce algorithms to train and generate with a diffusion model.
arXiv Detail & Related papers (2024-12-14T20:04:46Z) - Boosting Diffusion Models with Moving Average Sampling in Frequency Domain [101.43824674873508]
Diffusion models rely on the current sample to denoise the next one, possibly resulting in denoising instability.
In this paper, we reinterpret the iterative denoising process as model optimization and leverage a moving average mechanism to ensemble all the prior samples.
We name the complete approach "Moving Average Sampling in Frequency domain (MASF)"
arXiv Detail & Related papers (2024-03-26T16:57:55Z) - Particle Denoising Diffusion Sampler [32.310922004771776]
Particle Denoising Diffusion Sampler (PDDS) provides consistent estimates under mild assumptions.
We demonstrate PDDS on multimodal and high dimensional sampling tasks.
arXiv Detail & Related papers (2024-02-09T11:01:35Z) - A Geometric Perspective on Diffusion Models [57.27857591493788]
We inspect the ODE-based sampling of a popular variance-exploding SDE.
We establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm.
arXiv Detail & Related papers (2023-05-31T15:33:16Z) - Denoising Diffusion Samplers [41.796349001299156]
Denoising diffusion models are a popular class of generative models providing state-of-the-art results in many domains.
We explore a similar idea to sample approximately from unnormalized probability density functions and estimate their normalizing constants.
While score matching is not applicable in this context, we can leverage many of the ideas introduced in generative modeling for Monte Carlo sampling.
arXiv Detail & Related papers (2023-02-27T14:37:16Z) - Fast Inference in Denoising Diffusion Models via MMD Finetuning [23.779985842891705]
We present MMD-DDM, a novel method for fast sampling of diffusion models.
Our approach is based on the idea of using the Maximum Mean Discrepancy (MMD) to finetune the learned distribution with a given budget of timesteps.
Our findings show that the proposed method is able to produce high-quality samples in a fraction of the time required by widely-used diffusion models.
arXiv Detail & Related papers (2023-01-19T09:48:07Z) - From Denoising Diffusions to Denoising Markov Models [38.33676858989955]
Denoising diffusions are state-of-the-art generative models exhibiting remarkable empirical performance.
We propose a unifying framework generalising this approach to a wide class of spaces and leading to an original extension of score matching.
arXiv Detail & Related papers (2022-11-07T14:34:27Z) - Diffusion Models in Vision: A Survey [73.10116197883303]
A diffusion model is a deep generative model that is based on two stages, a forward diffusion stage and a reverse diffusion stage.
Diffusion models are widely appreciated for the quality and diversity of the generated samples, despite their known computational burdens.
arXiv Detail & Related papers (2022-09-10T22:00:30Z) - Generative Modeling with Denoising Auto-Encoders and Langevin Sampling [88.83704353627554]
We show that both DAE and DSM provide estimates of the score of the smoothed population density.
We then apply our results to the homotopy method of arXiv:1907.05600 and provide theoretical justification for its empirical success.
arXiv Detail & Related papers (2020-01-31T23:50:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.