{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T19:19:47Z","timestamp":1766171987218,"version":"3.48.0"},"reference-count":21,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/lsp.2025.3637667","type":"journal-article","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:07:43Z","timestamp":1764184063000},"page":"116-120","source":"Crossref","is-referenced-by-count":1,"title":["Gaussian Universality for Diffusion Models"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3232-9359","authenticated-orcid":false,"given":"Reza","family":"Ghane","sequence":"first","affiliation":[{"name":"Electrical Engineering Department, California Institute of Technology, Pasadena, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1162-564X","authenticated-orcid":false,"given":"Anthony","family":"Bao","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, University of Texas, Austin, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9238-9636","authenticated-orcid":false,"given":"Danil","family":"Akhtiamov","sequence":"additional","affiliation":[{"name":"Computing + Mathematical Sciences Department, California Institute of Technology, Pasadena, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1375-5838","authenticated-orcid":false,"given":"Babak","family":"Hassibi","sequence":"additional","affiliation":[{"name":"Electrical Engineering Department, California Institute of Technology, Pasadena, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02663"},{"key":"ref2","first-page":"8573","article-title":"Random matrix theory proves that deep learning representations of GAN-data behave as Gaussian mixtures","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Seddik","year":"2020"},{"article-title":"The underlying scaling laws and universal statistical structure of complex datasets","year":"2023","author":"Levi","key":"ref3"},{"article-title":"Perspectives on the state and future of deep learning2023","year":"2023","author":"Goldblum","key":"ref4"},{"article-title":"Towards an empirical theory of deep learning","year":"2021","author":"Nakkiran","key":"ref5"},{"key":"ref6","first-page":"8907","article-title":"Theoretical insights into multiclass classification: A high-dimensional asymptotic view","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Thrampoulidis","year":"2020"},{"key":"ref7","first-page":"10144","article-title":"Learning Gaussian mixtures with generalized linear models: Precise asymptotics in high-dimensions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Loureiro","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3637667"},{"key":"ref9","first-page":"18137","article-title":"Learning curves of generic features maps for realistic datasets with a teacher-student model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Loureiro","year":"2021"},{"key":"ref10","first-page":"426","article-title":"The Gaussian equivalence of generative models for learning with shallow neural networks","volume-title":"Proc. Math. Sci. Mach. Learn.","author":"Goldt","year":"2022"},{"key":"ref11","first-page":"54754","article-title":"Universality laws for Gaussian mixtures in generalized linear models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Dandi","year":"2023"},{"key":"ref12","first-page":"27680","article-title":"Are Gaussian data all you need? the extents and limits of universality in high-dimensional generalized linear estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pesce","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.109.034305"},{"key":"ref14","first-page":"125729","article-title":"Universality in transfer learning for linear models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Ghane","year":"2024"},{"key":"ref15","first-page":"1832","article-title":"Characterizing implicit bias in terms of optimization geometry","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gunasekar","year":"2018"},{"key":"ref16","article-title":"Stochastic gradient\/mirror descent: Minimax optimality and implicit regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Azizan","year":"2019"},{"key":"ref17","first-page":"4310","article-title":"Universality of empirical risk minimization","volume-title":"Proc. Conf. Learn. Theory","author":"Montanari","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1017\/9781108231596"},{"key":"ref19","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Karras","year":"2022"},{"key":"ref20","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/11304147\/11269808.pdf?arnumber=11269808","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T19:03:50Z","timestamp":1766171030000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11269808\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3637667","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2026]]}}}