English

Active Learning for Conditional Generative Compressed Sensing

Machine Learning 2026-05-08 v1 Numerical Analysis Numerical Analysis

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.

Keywords

Cite

@article{arxiv.2605.05435,
  title  = {Active Learning for Conditional Generative Compressed Sensing},
  author = {Alexander DeLise and Nick Dexter},
  journal= {arXiv preprint arXiv:2605.05435},
  year   = {2026}
}

Comments

33 pages, 11 figures

R2 v1 2026-07-01T12:53:41.538Z