Guardado en:
Detalles Bibliográficos
Autores principales: DeLise, Alexander, Dexter, Nick
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.05435
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915986617139200
author DeLise, Alexander
Dexter, Nick
author_facet DeLise, Alexander
Dexter, Nick
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_05435
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Active Learning for Conditional Generative Compressed Sensing
DeLise, Alexander
Dexter, Nick
Machine Learning
Numerical Analysis
68T07, 94A20, 65J22, 41A46, 68U10
I.2.6; I.4.5; G.1.6; G.3
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.
title Active Learning for Conditional Generative Compressed Sensing
topic Machine Learning
Numerical Analysis
68T07, 94A20, 65J22, 41A46, 68U10
I.2.6; I.4.5; G.1.6; G.3
url https://arxiv.org/abs/2605.05435