Demystifying Variational Diffusion Models

• URL: http://arxiv.org/abs/2401.06281v1
• Date: Thu, 11 Jan 2024 22:37:37 GMT
• Title: Demystifying Variational Diffusion Models
• Authors: Fabio De Sousa Ribeiro, Ben Glocker
• Abstract summary: We present a more straightforward introduction to diffusion models using directed graphical modelling and variational Bayesian principles. Our exposition constitutes a comprehensive technical review spanning from foundational concepts like deep latent variable models to recent advances in continuous-time diffusion-based modelling. We provide additional mathematical insights that were omitted in the seminal works whenever possible to aid in understanding, while avoiding the introduction of new notation.
• Score: 23.601173340762074
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the growing popularity of diffusion models, gaining a deep understanding of the model class remains somewhat elusive for the uninitiated in non-equilibrium statistical physics. With that in mind, we present what we believe is a more straightforward introduction to diffusion models using directed graphical modelling and variational Bayesian principles, which imposes relatively fewer prerequisites on the average reader. Our exposition constitutes a comprehensive technical review spanning from foundational concepts like deep latent variable models to recent advances in continuous-time diffusion-based modelling, highlighting theoretical connections between model classes along the way. We provide additional mathematical insights that were omitted in the seminal works whenever possible to aid in understanding, while avoiding the introduction of new notation. We envision this article serving as a useful educational supplement for both researchers and practitioners in the area, and we welcome feedback and contributions from the community at https://github.com/biomedia-mira/demystifying-diffusion.

Related papers

• Alignment of Diffusion Models: Fundamentals, Challenges, and Future [28.64041196069495]
  Diffusion models have emerged as the leading paradigm in generative modeling, excelling in various applications. Despite their success, these models often misalign with human intentions, generating outputs that may not match text prompts or possess desired properties. Inspired by the success of alignment in tuning large language models, recent studies have investigated aligning diffusion models with human expectations and preferences.
  arXiv  Detail & Related papers  (2024-09-11T13:21:32Z)
• Diffusion Models in Low-Level Vision: A Survey [82.77962165415153]
  diffusion model-based solutions have emerged as widely acclaimed for their ability to produce samples of superior quality and diversity. We present three generic diffusion modeling frameworks and explore their correlations with other deep generative models. We summarize extended diffusion models applied in other tasks, including medical, remote sensing, and video scenarios.
  arXiv  Detail & Related papers  (2024-06-17T01:49:27Z)
• An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization [59.63880337156392]
  Diffusion models have achieved tremendous success in computer vision, audio, reinforcement learning, and computational biology. Despite the significant empirical success, theory of diffusion models is very limited. This paper provides a well-rounded theoretical exposure for stimulating forward-looking theories and methods of diffusion models.
  arXiv  Detail & Related papers  (2024-04-11T14:07:25Z)
• Latent Diffusion Counterfactual Explanations [28.574246724214962]
  We introduce Latent Diffusion Counterfactual Explanations (LDCE) LDCE harnesses the capabilities of recent class- or text-conditional foundation latent diffusion models to expedite counterfactual generation. We show how LDCE can provide insights into model errors, enhancing our understanding of black-box model behavior.
  arXiv  Detail & Related papers  (2023-10-10T14:42:34Z)
• On the Equivalence of Consistency-Type Models: Consistency Models, Consistent Diffusion Models, and Fokker-Planck Regularization [68.13034137660334]
  We propose theoretical connections between three recent consistency'' notions designed to enhance diffusion models for distinct objectives. Our insights offer the potential for a more comprehensive and encompassing framework for consistency-type models.
  arXiv  Detail & Related papers  (2023-06-01T05:57:40Z)
• Diffusion Models for Time Series Applications: A Survey [23.003273147019446]
  Diffusion models are used in image, video, and text synthesis nowadays. We focus on diffusion-based methods for time series forecasting, imputation, and generation. We conclude the common limitation of diffusion-based methods and highlight potential future research directions.
  arXiv  Detail & Related papers  (2023-05-01T02:06:46Z)
• Diffusion Models in Vision: A Survey [80.82832715884597]
  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)
• How Much is Enough? A Study on Diffusion Times in Score-based Generative Models [76.76860707897413]
  Current best practice advocates for a large T to ensure that the forward dynamics brings the diffusion sufficiently close to a known and simple noise distribution. We show how an auxiliary model can be used to bridge the gap between the ideal and the simulated forward dynamics, followed by a standard reverse diffusion process.
  arXiv  Detail & Related papers  (2022-06-10T15:09:46Z)
• Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations [64.85696493596821]
  In computer vision applications, generative counterfactual methods indicate how to perturb a model's input to change its prediction. We propose a counterfactual method that learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss. Our model improves the success rate of producing high-quality valuable explanations when compared to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-03-18T12:57:34Z)

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.