arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.09757cs.LGstat.ML
收藏

关于在非高斯噪声下核回归的统一误差界

On Uniform Error Bounds for Kernel Regression under Non-Gaussian Noise

Chair of Automatic Control Engineering, Department of Computer Engineering, Technical University of Munich(自动控制工程学系,计算机工程系,慕尼黑技术大学);Institute of Control Systems, Hamburg University of Technology(控制系统研究所,汉堡技术大学);Department of Electrical and Computer Engineering, National University of Singapore(电子与计算机工程系,新加坡国立大学)

Johannes Teutsch, Oleksii Molodchyk, Marion Leibold, Timm Faulwasser, Armin Lederer

AI总结:

本文提出非渐近的核回归统一误差界,适用于广泛非高斯分布,包括亚高斯、有界、亚指数和方差/矩有界的噪声,并在安全控制中验证了界的有效性。

摘要:

为从噪声观测中获得的函数估计提供非保守的不确定性量化仍然是统计机器学习中的基本挑战,尤其是在安全关键领域。本文提出新颖的非渐近概率统一误差界用于基于核的回归。与文献中仅限于(条件性)独立亚高斯噪声的相关界不同,我们的界允许考虑广泛非高斯分布,如亚高斯、有界、亚指数和方差/矩有界的噪声。此外,我们的结果适用于相关和不相关的噪声。我们比较了所提误差界与现有结果在诱导不确定性区域和安全控制中的性能,证明了所提界的紧致性。

英文摘要:

Providing non-conservative uncertainty quantification for function estimates derived from noisy observations remains a fundamental challenge in statistical machine learning, particularly for applications in safety-critical domains. In this work, we propose novel non-asymptotic probabilistic uniform error bounds for kernel-based regression. Compared to related bounds in the literature that are restricted to (conditionally) independent sub-Gaussian noise, our bounds allow to consider a broad class of non-Gaussian distributions, such as sub-Gaussian, bounded, sub-exponential, and variance/moment-bounded noise. Moreover, our results apply to correlated and uncorrelated noise. We compare our proposed error bounds with existing results in terms of the induced uncertainty region and their performance in safe control, demonstrating the tightness of the proposed bounds.

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。

↑