Diffusion models as plug-and-play priors

[2206.09012] Diffusion models as plug-and-play priors Skip to main content Search Submit Donate Log in Computer Science > Machine Learning arXiv:2206.09012 (cs) [Submitted on 17 Jun 2022 ( v1 ), last revised 28 Aug 2026 (this version, v4)] Title: Diffusion models as plug-and-play priors Authors: Alexandros Graikos , Esmeralda S. Whitammer , Nebojsa Jojic , Dimitris Samaras View PDF HTML (experimental) Abstract: We consider the problem of inferring high-dimensional data $\mathbf{x}$ in a model that consists of a prior $p(\mathbf{x})$ and an auxiliary differentiable constraint $c(\mathbf{x},\mathbf{y})$ on $x$ given some additional information $\mathbf{y}$. In this paper, the prior is an independently trained denoising diffusion generative model. The auxiliary constraint is expected to have a differentiable form, but can come from diverse sources. The possibility of such inference turns diffusion models into plug-and-play modules, thereby allowing a range of potential applications in adapting models to new domains and tasks, such as conditional generation or image segmentation. The structure of diffusion models allows us to perform approximate inference by iterating differentiation through the fixed denoising network enriched with different amounts of noise at each step. Considering many noised versions of $\mathbf{x}$ in evaluation of its fitness is a novel search mechanism that may lead to new algorithms for solving combinatorial optimization problems. Comments: NeurIPS 2022; code: this https URL Subjects: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2206.09012 [cs.LG] (or arXiv:2206.09012v4 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2206.09012 Focus to learn more arXiv-issued DOI via DataCite Related DOI : https://doi.org/10.52202/068431-1070 Focus to learn more DOI(s) linking to related resources Submission history From: Esmeralda Whitammer [ view email ] [v1] Fri, 17 Jun 2022 21:11:36 UTC (10,725 KB) [v2] Wed, 12 Oct 2022 18:50:21 UTC (10,756 KB) [v3] Sun, 8 Jan 2023 23:21:37 UTC (10,756 KB) [v4] Fri, 28 Aug 2026 06:06:49 UTC (7,886 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.LG < prev | next > new | recent | 2022-06 Change to browse by: cs cs.CV References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Diffusion models as plug-and-play priors#684142
• Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit Correction#259490
• Diffusion Language Models for Speech Recognition#14019
• The Seriality Gap in Video Diffusion Models#366237
• Constrained Denoising, Empirical Bayes, and Optimal Transport#996866