{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:47:14Z","timestamp":1785422834624,"version":"3.56.0"},"reference-count":27,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T00:00:00Z","timestamp":1781136000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["NSF AI Institute (AI-EDGE) 2112471"],"award-info":[{"award-number":["NSF AI Institute (AI-EDGE) 2112471"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["ExpandAI-2324052"],"award-info":[{"award-number":["ExpandAI-2324052"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["ECCS-2413528"],"award-info":[{"award-number":["ECCS-2413528"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2312836"],"award-info":[{"award-number":["CNS-2312836"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2223452"],"award-info":[{"award-number":["CNS-2223452"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2225561"],"award-info":[{"award-number":["CNS-2225561"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["CCF-2232907"],"award-info":[{"award-number":["CCF-2232907"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["ECCS-2448268"],"award-info":[{"award-number":["ECCS-2448268"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"award":["NSF AI Institute (AI-EDGE) 2112471"],"award-info":[{"award-number":["NSF AI Institute (AI-EDGE) 2112471"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]},{"award":["ExpandAI-2324052"],"award-info":[{"award-number":["ExpandAI-2324052"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]},{"award":["ECCS-2413528"],"award-info":[{"award-number":["ECCS-2413528"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]},{"award":["CNS-2312836"],"award-info":[{"award-number":["CNS-2312836"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]},{"award":["CNS-2223452"],"award-info":[{"award-number":["CNS-2223452"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]},{"award":["CNS-2225561"],"award-info":[{"award-number":["CNS-2225561"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]},{"award":["CCF-2232907"],"award-info":[{"award-number":["CCF-2232907"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]},{"award":["ECCS-2448268"],"award-info":[{"award-number":["ECCS-2448268"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"DEVCOM Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-23-2-0225"],"award-info":[{"award-number":["W911NF-23-2-0225"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"award":["W911NF-23-2-0225"],"award-info":[{"award-number":["W911NF-23-2-0225"]}],"id":[{"id":"https:\/\/ror.org\/011hc8f90","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Discrete diffusion models have become an important class of generative models for categorical data, yet their theoretical understanding remains largely limited to time-homogeneous noise schedules. In this work, we study uniform-rate discrete diffusion models with time-inhomogeneous continuous-time Markov chain forward processes. We establish convergence guarantees for practical reverse-time samplers by directly controlling the total variation distance, avoiding the indirect route of first bounding KL divergence and then applying Pinsker\u2019s inequality. Our analysis decomposes the sampling error into initialization, score-estimation, discretization, and early-stopping errors, and explicitly characterizes how each term depends on the accumulated noise, the local noise rate, and the smoothness of the noise schedule. Under suitable regularity conditions on the noise schedule, we further derive step-complexity guarantees that match the order of existing results for homogeneous samplers.<\/jats:p>","DOI":"10.3390\/e28060675","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T09:06:52Z","timestamp":1781600812000},"page":"675","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Convergence Guarantees for Time-Inhomogeneous Uniform-Rate Discrete Diffusion Models"],"prefix":"10.3390","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7128-3712","authenticated-orcid":false,"given":"Yuchen","family":"Liang","sequence":"first","affiliation":[{"name":"Luddy School of Informatics, Computing, and Engineering, Indiana University Indianapolis, Indianapolis, IN 46202, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lifeng","family":"Lai","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, UC Davis, Davis, CA 95616, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ness","family":"Shroff","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH 43210, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingbin","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH 43210, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,11]]},"reference":[{"key":"ref_1","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., and Ganguli, S. (2015, January 7\u20139). Deep Unsupervised Learning using Nonequilibrium Thermodynamics. Proceedings of the 32nd International Conference on Machine Learning, Lille, France."},{"key":"ref_2","first-page":"6840","article-title":"Denoising Diffusion Probabilistic Models","volume":"33","author":"Ho","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref_3","unstructured":"Beygelzimer, A., Dauphin, Y., Liang, P., and Vaughan, J.W. (2021). Structured Denoising Diffusion Models in Discrete State-Spaces. Proceedings of the Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_4","unstructured":"Dhariwal, P., and Nichol, A.Q. (2021). Diffusion Models Beat GANs on Image Synthesis. Proceedings of the Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_5","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., and Chen, M. (2022). Hierarchical Text-Conditional Image Generation with CLIP Latents. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B. (2022). High-Resolution Image Synthesis with Latent Diffusion Models. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 18\u201324 June 2022, IEEE.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref_7","unstructured":"Huang, R., Huang, J., Yang, D., Ren, Y., Liu, L., Li, M., Ye, Z., Liu, J., Yin, X., and Zhao, Z. (2023, January 23\u201329). Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models. Proceedings of the International Conference on Machine Learning, Honolulu, HI, USA."},{"key":"ref_8","unstructured":"Lou, A., Meng, C., and Ermon, S. (2024, January 21\u201327). Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution. Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Liu, C., Fan, W., Liu, Y., Li, J., Li, H., Liu, H., Tang, J., and Li, Q. (2023, January 19\u201325). Generative diffusion models on graphs: Methods and applications. Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, Macao, China.","DOI":"10.24963\/ijcai.2023\/751"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"7238","DOI":"10.1021\/acs.jcim.4c01107","article-title":"Diffusion Models in De Novo Drug Design","volume":"64","author":"Alakhdar","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"ref_11","unstructured":"Campbell, A., Benton, J., Bortoli, V.D., Rainforth, T., Deligiannidis, G., and Doucet, A. (2022). A Continuous Time Framework for Discrete Denoising Models. Proceedings of the Advances in Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Chen, H., and Ying, L. (2024). Convergence Analysis of Discrete Diffusion Model: Exact Implementation through Uniformization. arXiv.","DOI":"10.4208\/jml.240812"},{"key":"ref_13","unstructured":"Zhang, Z., Chen, Z., and Gu, Q. (2025, January 24\u201328). Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis. Proceedings of the Thirteenth International Conference on Learning Representations, Singapore."},{"key":"ref_14","unstructured":"Pham, L.T.N., Shariatian, D., Ocello, A., Conforti, G., and Durmus, A.O. (2025, January 13\u201319). Discrete Markov Probabilistic Models: An Improved Discrete Score-Based Framework with sharp convergence bounds under minimal assumptions. Proceedings of the Forty-Second International Conference on Machine Learning, Vancouver, BC, Canada."},{"key":"ref_15","unstructured":"Dmitriev, D., Huang, Z., and Wei, Y. (2026). Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees. arXiv."},{"key":"ref_16","unstructured":"Ren, Y., Chen, H., Rotskoff, G.M., and Ying, L. (2025, January 24\u201328). How Discrete and Continuous Diffusion Meet: Comprehensive Analysis of Discrete Diffusion Models via a Stochastic Integral Framework. Proceedings of the Thirteenth International Conference on Learning Representations, Singapore."},{"key":"ref_17","unstructured":"Liang, Y., Liang, Y., Lai, L., and Shroff, N. (2025, January 2\u20137). Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees. Proceedings of the Thirty-Ninth Annual Conference on Neural Information Processing Systems, San Diego, CA, USA."},{"key":"ref_18","unstructured":"Liang, Y., Tan, Z., Shroff, N., and Liang, Y. (2026). Sharp Convergence Rates for Masked Diffusion Models. arXiv."},{"key":"ref_19","unstructured":"Chen, T. (2023). On the Importance of Noise Scheduling for Diffusion Models. arXiv."},{"key":"ref_20","unstructured":"Conforti, G., Durmus, A., Pham, L.T.N., and Raoul, G. (2025). Non-Asymptotic Convergence of Discrete Diffusion Models: Masked and Random Walk dynamics. arXiv."},{"key":"ref_21","unstructured":"Ren, Y., Chen, H., Zhu, Y., Guo, W., Chen, Y., Rotskoff, G.M., Tao, M., and Ying, L. (2025). Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithms. Proceedings of the Advances in Neural Information Processing Systems 38 (NeurIPS 2025), Curran Associates, Inc."},{"key":"ref_22","unstructured":"Liang, Y., Shroff, N., and Liang, Y. (2026). From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models. arXiv."},{"key":"ref_23","unstructured":"Nisonoff, H., Xiong, J., Allenspach, S., and Listgarten, J. (2025, January 24\u201328). Unlocking Guidance for Discrete State-Space Diffusion and Flow Models. Proceedings of the Thirteenth International Conference on Learning Representations, Singapore."},{"key":"ref_24","unstructured":"Kan, K., Li, X., Zhang, B.J., Sahai, T., Osher, S., and Katsoulakis, M.A. (2026). Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space. arXiv."},{"key":"ref_25","unstructured":"Liang, Y., Huang, R., Lai, L., Shroff, N., and Liang, Y. (2025). Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models. Proceedings of the Thirty-Ninth Annual Conference on Neural Information Processing Systems, Curran Associates, Inc."},{"key":"ref_26","unstructured":"Huang, X., Lin, Y., Jain, N., Wang, K., Zou, D., Ma, Y., and Zhang, T. (2025). On the Complexity Theory of Masked Discrete Diffusion: From poly(1\/\u03f5) to Nearly \u03f5-Free. arXiv."},{"key":"ref_27","unstructured":"Kelly, F.P. (2011). Reversibility and Stochastic Networks, Cambridge University Press."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/6\/675\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T09:24:39Z","timestamp":1781601879000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/6\/675"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,11]]},"references-count":27,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["e28060675"],"URL":"https:\/\/doi.org\/10.3390\/e28060675","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,11]]}}}