Neural Diffusion Models
- URL: http://arxiv.org/abs/2310.08337v3
- Date: Sat, 1 Jun 2024 09:56:39 GMT
- Title: Neural Diffusion Models
- Authors: Grigory Bartosh, Dmitry Vetrov, Christian A. Naesseth,
- Abstract summary: We present a generalization of conventional diffusion models that enables defining and learning time-dependent non-linear transformations of data.
NDMs outperform conventional diffusion models in terms of likelihood and produce high-quality samples.
- Score: 2.1779479916071067
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Diffusion models have shown remarkable performance on many generative tasks. Despite recent success, most diffusion models are restricted in that they only allow linear transformation of the data distribution. In contrast, broader family of transformations can potentially help train generative distributions more efficiently, simplifying the reverse process and closing the gap between the true negative log-likelihood and the variational approximation. In this paper, we present Neural Diffusion Models (NDMs), a generalization of conventional diffusion models that enables defining and learning time-dependent non-linear transformations of data. We show how to optimise NDMs using a variational bound in a simulation-free setting. Moreover, we derive a time-continuous formulation of NDMs, which allows fast and reliable inference using off-the-shelf numerical ODE and SDE solvers. Finally, we demonstrate the utility of NDMs with learnable transformations through experiments on standard image generation benchmarks, including CIFAR-10, downsampled versions of ImageNet and CelebA-HQ. NDMs outperform conventional diffusion models in terms of likelihood and produce high-quality samples.
Related papers
- Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling [2.1779479916071067]
We introduce a novel framework that enhances diffusion models by supporting a broader range of forward processes.
We also propose a novel parameterization technique for learning the forward process.
Results underscore NFDM's versatility and its potential for a wide range of applications.
arXiv Detail & Related papers (2024-04-19T15:10:54Z) - Fast Sampling via Discrete Non-Markov Diffusion Models [49.598085130313514]
We propose a discrete non-Markov diffusion model, which admits an accelerated reverse sampling for discrete data generation.
Our method significantly reduces the number of function evaluations (i.e., calls to the neural network), making the sampling process much faster.
arXiv Detail & Related papers (2023-12-14T18:14:11Z) - Gaussian Mixture Solvers for Diffusion Models [84.83349474361204]
We introduce a novel class of SDE-based solvers called GMS for diffusion models.
Our solver outperforms numerous SDE-based solvers in terms of sample quality in image generation and stroke-based synthesis.
arXiv Detail & Related papers (2023-11-02T02:05:38Z) - Diffusion models for probabilistic programming [56.47577824219207]
Diffusion Model Variational Inference (DMVI) is a novel method for automated approximate inference in probabilistic programming languages (PPLs)
DMVI is easy to implement, allows hassle-free inference in PPLs without the drawbacks of, e.g., variational inference using normalizing flows, and does not make any constraints on the underlying neural network model.
arXiv Detail & Related papers (2023-11-01T12:17:05Z) - DiffFlow: A Unified SDE Framework for Score-Based Diffusion Models and
Generative Adversarial Networks [41.451880167535776]
We propose a unified theoretic framework for explicit generative models (SDMs) and generative adversarial nets (GANs)
Under our unified theoretic framework, we introduce several instantiations of the DiffFLow that provide new algorithms beyond GANs and SDMs with exact likelihood inference.
arXiv Detail & Related papers (2023-07-05T10:00:53Z) - Semi-Implicit Denoising Diffusion Models (SIDDMs) [50.30163684539586]
Existing models such as Denoising Diffusion Probabilistic Models (DDPM) deliver high-quality, diverse samples but are slowed by an inherently high number of iterative steps.
We introduce a novel approach that tackles the problem by matching implicit and explicit factors.
We demonstrate that our proposed method obtains comparable generative performance to diffusion-based models and vastly superior results to models with a small number of sampling steps.
arXiv Detail & Related papers (2023-06-21T18:49:22Z) - Reflected Diffusion Models [93.26107023470979]
We present Reflected Diffusion Models, which reverse a reflected differential equation evolving on the support of the data.
Our approach learns the score function through a generalized score matching loss and extends key components of standard diffusion models.
arXiv Detail & Related papers (2023-04-10T17:54:38Z) - Information-Theoretic Diffusion [18.356162596599436]
Denoising diffusion models have spurred significant gains in density modeling and image generation.
We introduce a new mathematical foundation for diffusion models inspired by classic results in information theory.
arXiv Detail & Related papers (2023-02-07T23:03:07Z) - 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) - Diffusion Glancing Transformer for Parallel Sequence to Sequence
Learning [52.72369034247396]
We propose the diffusion glancing transformer, which employs a modality diffusion process and residual glancing sampling.
DIFFGLAT achieves better generation accuracy while maintaining fast decoding speed compared with both autoregressive and non-autoregressive models.
arXiv Detail & Related papers (2022-12-20T13:36:25Z)
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.