{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T05:04:07Z","timestamp":1781327047739,"version":"3.54.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"High-Performance Computing Platform of Peking University. The work of Jiaoyang Huang was supported in part by NSF","award":["DMS-2331096"],"award-info":[{"award-number":["DMS-2331096"]}]},{"name":"High-Performance Computing Platform of Peking University"},{"name":"NSF","award":["DMS-2331096"],"award-info":[{"award-number":["DMS-2331096"]}]},{"name":"Sloan Research Fellowship."}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tit.2025.3557050","type":"journal-article","created":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T21:36:31Z","timestamp":1743629791000},"page":"4581-4601","source":"Crossref","is-referenced-by-count":6,"title":["Convergence Analysis of Probability Flow ODE for Score-Based Generative Models"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6072-9352","authenticated-orcid":false,"given":"Daniel Zhengyu","family":"Huang","sequence":"first","affiliation":[{"name":"Beijing International Center for Mathematical Research and the Center for Machine Learning Research, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaoyang","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Statistics and Data Science, University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6912-8024","authenticated-orcid":false,"given":"Zhengjiang","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref2","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref3","first-page":"695","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Song"},{"key":"ref4","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv:2011.13456"},{"key":"ref5","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref7","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow"},{"key":"ref8","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"37","author":"Rezende"},{"issue":"57","key":"ref9","first-page":"1","article-title":"Normalizing flows for probabilistic modeling and inference","volume":"22","author":"Papamakarios","year":"2021","journal-title":"J. Mach. Learn. Res."},{"issue":"4","key":"ref10","first-page":"695","article-title":"Estimation of non-normalized statistical models by score matching","volume":"6","author":"Hyv\u00e4rinen","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref12","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020","journal-title":"arXiv:2005.00341"},{"key":"ref13","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Popov"},{"key":"ref14","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref15","first-page":"1","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Esser"},{"key":"ref16","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref17","first-page":"5775","article-title":"DPM-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"L\u00fc"},{"key":"ref18","article-title":"DPM-Solver++: Fast solver for guided sampling of diffusion probabilistic models","author":"Lu","year":"2022","journal-title":"arXiv:2211.01095"},{"key":"ref19","article-title":"Fast sampling of diffusion models with exponential integrator","author":"Zhang","year":"2022","journal-title":"arXiv:2204.13902"},{"key":"ref20","article-title":"UniPC: A unified predictor-corrector framework for fast sampling of diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhao"},{"key":"ref21","article-title":"Generative modeling with denoising auto-encoders and Langevin sampling","author":"Block","year":"2020","journal-title":"arXiv:2002.00107"},{"key":"ref22","first-page":"17695","article-title":"Diffusion Schr\u00f6dinger bridge with applications to score-based generative modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"De Bortoli"},{"key":"ref23","article-title":"Convergence of the inexact Langevin algorithm and score-based generative models in KL divergence","author":"Yingxi Yang","year":"2022","journal-title":"arXiv:2211.01512"},{"key":"ref24","first-page":"20205","article-title":"Score-based generative modeling secretly minimizes the Wasserstein distance","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Kwon"},{"key":"ref25","article-title":"Contractive diffusion probabilistic models","author":"Tang","year":"2024","journal-title":"arXiv:2401.13115"},{"key":"ref26","first-page":"22870","article-title":"Convergence for score-based generative modeling with polynomial complexity","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Lee"},{"key":"ref27","article-title":"Sampling is as easy as learning the score: Theory for diffusion models with minimal data assumptions","author":"Chen","year":"2022","journal-title":"arXiv:2209.11215"},{"key":"ref28","first-page":"946","article-title":"Convergence of score-based generative modeling for general data distributions","volume-title":"Proc. Int. Conf. Algorithmic Learn. Theory","author":"Lee"},{"key":"ref29","first-page":"4672","article-title":"Score approximation, estimation and distribution recovery of diffusion models on low-dimensional data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref30","first-page":"4735","article-title":"Improved analysis of score-based generative modeling: User-friendly bounds under minimal smoothness assumptions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref31","article-title":"Theoretical insights for diffusion guidance: A case study for Gaussian mixture models","author":"Wu","year":"2024","journal-title":"arXiv:2403.01639"},{"key":"ref32","article-title":"Score-based diffusion models via stochastic differential equations\u2014A technical tutorial","author":"Tang","year":"2024","journal-title":"arXiv:2402.07487"},{"key":"ref33","article-title":"Global well-posedness and convergence analysis of score-based generative models via sharp Lipschitz estimates","author":"Mooney","year":"2024","journal-title":"arXiv:2405.16104"},{"key":"ref34","first-page":"4462","article-title":"Restoration-degradation beyond linear diffusions: A non-asymptotic analysis for DDIM-type samplers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref35","article-title":"The probability flow ODE is provably fast","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Chen"},{"key":"ref36","article-title":"Accelerating convergence of score-based diffusion models, provably","author":"Li","year":"2024","journal-title":"arXiv:2403.03852"},{"key":"ref37","article-title":"Towards faster non-asymptotic convergence for diffusion-based generative models","author":"Li","year":"2023","journal-title":"arXiv:2306.09251"},{"key":"ref38","article-title":"Building normalizing flows with stochastic interpolants","author":"Albergo","year":"2022","journal-title":"arXiv:2209.15571"},{"key":"ref39","article-title":"Error bounds for flow matching methods","author":"Benton","year":"2023","journal-title":"arXiv:2305.16860"},{"key":"ref40","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv:2210.02747"},{"key":"ref41","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"arXiv:2209.03003"},{"key":"ref42","article-title":"Stochastic interpolants: A unifying framework for flows and diffusions","author":"Albergo","year":"2023","journal-title":"arXiv:2303.08797"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ace2aa"},{"key":"ref44","article-title":"Convergence analysis for general probability flow ODEs of diffusion models in Wasserstein distances","author":"Gao","year":"2024","journal-title":"arXiv:2401.17958"},{"key":"ref45","first-page":"5301","article-title":"On the spectral bias of neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rahaman"},{"key":"ref46","article-title":"Frequency principle: Fourier analysis sheds light on deep neural networks","author":"John Xu","year":"2019","journal-title":"arXiv:1901.06523"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9991(74)90019-9"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140919"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s00222-004-0367-2"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.4171\/zaa\/1681"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/18\/11011509\/10947535.pdf?arnumber=10947535","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T17:04:09Z","timestamp":1748019849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10947535\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":50,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tit.2025.3557050","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"value":"0018-9448","type":"print"},{"value":"1557-9654","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}