arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2505.21135cs.LGcs.CVstat.ML
收藏

使用扩散先验学习单指数模型

Learning Single Index Models with Diffusion Priors

Anqi Tang(安琪·塔恩);Youming Chen(欧阳明·陈);Shuchen Xue(苏晨·薛);Zhaoqiang Liu(刘兆强)

Anqi Tang, Youming Chen, Shuchen Xue, Zhaoqiang Liu

AI总结:

本文提出一种基于扩散模型(DMs)先验的高效重建方法,用于解决具有不连续或未知链接函数的半参数单指数模型信号恢复问题,仅需一轮无条件采样和部分反演,在保证更高重建精度的同时显著减少了神经函数评估次数。

摘要:

扩散模型(DMs)通过高效建模复杂数据分布,展现了生成多样且高质量图像的卓越能力。它们也被探索作为信号恢复的强大生成先验,从而大幅提升了重建信号的质量。然而,现有的基于扩散模型的信号恢复研究要么专注于特定的重建问题,要么无法处理具有不连续或未知链接函数的非线性测量模型。在本工作中,我们专注于使用DMs实现从半参数单指数模型中的精确恢复,该模型涵盖了多种可能具有不连续和未知链接函数的流行非线性模型。我们提出了一种高效的重建方法,仅需一轮无条件采样和DMs的(部分)反演。在适当条件下,已建立了关于所提方法有效性的理论分析。我们在图像数据集上针对不同的非线性测量模型进行了数值实验。我们观察到,与竞争方法相比,我们的方法能够产生更准确的重建,同时显著减少了神经函数评估次数。

英文摘要:

Diffusion models (DMs) have demonstrated remarkable ability to generate diverse and high-quality images by efficiently modeling complex data distributions. They have also been explored as powerful generative priors for signal recovery, resulting in a substantial improvement in the quality of reconstructed signals. However, existing research on signal recovery with diffusion models either focuses on specific reconstruction problems or is unable to handle nonlinear measurement models with discontinuous or unknown link functions. In this work, we focus on using DMs to achieve accurate recovery from semi-parametric single index models, which encompass a variety of popular nonlinear models that may have {\em discontinuous} and {\em unknown} link functions. We propose an efficient reconstruction method that only requires one round of unconditional sampling and (partial) inversion of DMs. Theoretical analysis on the effectiveness of the proposed methods has been established under appropriate conditions. We perform numerical experiments on image datasets for different nonlinear measurement models. We observe that compared to competing methods, our approach can yield more accurate reconstructions while utilizing significantly fewer neural function evaluations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑