Abstract:Generative compressed sensing uses the range of a pretrained generator as a nonlinear model for recovering structured signals from limited measurements. We study a conditional version of this problem for image recovery from subsampled Fourier measurements using prompt-conditioned generative models. Our framework separates two roles of conditioning: the prompt used to design the sampling distribution and the prompt used to define the recovery model. For ReLU and Lipschitz conditional generators, we prove stable recovery bounds showing that prompt-matched Christoffel sampling retains the same Christoffel complexity constant as existing near-optimal generative compressed sensing theory, while prompt mismatch incurs an explicit compatibility penalty. Experiments with Stable Diffusion show that prompts meaningfully reshape Christoffel sampling distributions and influence image recovery. Overall, our results suggest that prompts should be treated as design variables with distinct effects on sensing, approximation, and recovery.
| Comments: | 33 pages, 11 figures |
| Subjects: | Machine Learning (cs.LG); Numerical Analysis (math.NA) |
| MSC classes: | 68T07, 94A20, 65J22, 41A46, 68U10 |
| ACM classes: | I.2.6; I.4.5; G.1.6; G.3 |
| Cite as: | arXiv:2605.05435 [cs.LG] |
| (or arXiv:2605.05435v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.05435 arXiv-issued DOI via DataCite (pending registration) |
From: Nick Dexter [view email]
[v1]
Wed, 6 May 2026 20:50:14 UTC (36,816 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。