[2604.02482] SEDGE: Structural Extrapolated Data Generation

Computer Science > Machine Learning arXiv:2604.02482 (cs) [Submitted on 2 Apr 2026] Title:SEDGE: Structural Extrapolated Data Generation Authors:Kun Zhang, Jiaqi Sun, Yiqing Li, Ignavier Ng, Namrata Deka, Shaoan Xie View a PDF of the paper titled SEDGE: Structural Extrapolated Data Generation, by Kun Zhang and 5 other authors View PDF HTML (experimental) Abstract:This paper proposes a framework for Structural Extrapolated Data GEneration (SEDGE) based on suitable assumptions on the underlying data generating process. We provide conditions under which data satisfying new specifications can be generated reliably, together with the approximate identifiability of the distribution of such data under certain ``conservative" assumptions. On the algorithmic side, we develop practical methods to achieve extrapolated data generation, based on the structure-informed optimization strategy or diffusion posterior sampling, respectively. We verify the extrapolation performance on synthetic data and also consider extrapolated image generation as a real-world scenario to illustrate the validity of the proposed framework. Subjects: Machine Learning (cs.LG) Cite as: arXiv:2604.02482 [cs.LG]   (or arXiv:2604.02482v1 [cs.LG] for this version)   https://doi.org/10.48550/arXiv.2604.02482 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Jiaqi Sun [view email] [v1] Thu, 2 Apr 2026 19:30:24 UTC (17,320 KB) Full-text links: Access Paper: View a PDF of...