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 2602.02045cs.LG
收藏

鲁棒扩散后验采样用于贝叶斯逆问题

Outlier-robust Diffusion Posterior Sampling for Bayesian Inverse Problems

University College London(伦敦大学学院);Imperial College London(伦敦帝国学院);Shanghai University of Finance and Economics(上海金融学院)

Yiming Yang, Xiaoyuan Cheng, Yi He, Kaiyu Li, Wenxuan Yuan, Zhuo Sun

AI总结:

本文提出鲁棒扩散后验采样方法,通过分析后验偏差和稳定性,解决逆问题中异常值对扩散求解器的影响,提升线性和非线性任务的鲁棒性。

摘要:

扩散模型已发展为强大的学习先验用于贝叶斯逆问题(BIPs)。基于扩散的求解器依赖于对观测的假设似然来指导生成过程。似然不准确在实际BIPs中很常见,已知会降低恢复性能,尤其是在异常值污染下。我们通过首先表征诱导的后验偏差并证明线性BIPs中扩散求解器的稳定性来研究此问题。我们的稳定性分析进一步揭示了现有扩散求解器在异常值污染测量下的潜在鲁棒性缺陷。为了解决这个问题,我们提出了一种简单而有效的解决方案:鲁棒扩散后验采样,它在线性BIPs中被证明是鲁棒的,并且与现有基于梯度的后验采样器兼容。科学逆问题和自然图像任务的实验证明了我们方法的有效性和鲁棒性,在包含异常值污染的挑战性场景中,线性和非线性任务均表现出一致的性能提升。

英文摘要:

Diffusion models have emerged as powerful learned priors for Bayesian inverse problems (BIPs). Diffusion-based solvers rely on a presumed likelihood for the observations in BIPs to guide the generation process. Likelihood misspecification is common in practical BIPs and is known to degrade recovery performance, particularly under outlier contamination. We investigate this problem by first characterizing the induced posterior deviation and proving the stability of diffusion-based solvers for linear BIPs. Our stability analysis further reveals potential robustness deficiencies of existing diffusion-based solvers under outlier-contaminated measurements. To address this issue, we propose a simple yet effective solution: robust diffusion posterior sampling, which is provably outlier-robust for linear BIPs and compatible with existing gradient-based posterior samplers. Empirical results from scientific inverse problems and natural image tasks demonstrate the effectiveness and robustness of our method, with consistent performance gains in challenging scenarios involving outlier contamination for both linear and nonlinear tasks.

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。

↑