arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.19950cs.LG
收藏

面向分布外数据的覆盖保证预测集

Coverage-Guaranteed Prediction Sets for Out-of-Distribution Data

Wuhan University(武汉大学)

Xin Zou, Weiwei Liu

AI总结:

本文针对分布外场景中分裂共形预测因可交换性假设失效而无法保证覆盖的问题,提出一种新的置信预测集构造方法,并给出理论证明和模拟实验验证。

摘要:

分布外(OOD)泛化近年来因其在现实应用中有前景的实验结果而吸引了越来越多的研究关注。本文研究OOD泛化设置下的置信集预测问题。分裂共形预测(SCP)是处理置信集预测问题的一种高效框架。然而,SCP的有效性要求样本具有可交换性,而这一条件在OOD设置下并不成立。实验上,我们表明当未见目标域与源域不同时,直接应用SCP会导致无法维持边际覆盖。为解决这一问题,我们提出了一种在OOD设置下构造置信预测集的方法,并从理论上证明了该方法的有效性。最后,我们在模拟数据上进行了实验,以实证验证我们理论的正确性以及所提方法的有效性。

英文摘要:

Out-of-distribution (OOD) generalization has attracted increasing research attention in recent years, due to its promising experimental results in real-world applications. In this paper,we study the confidence set prediction problem in the OOD generalization setting. Split conformal prediction (SCP) is an efficient framework for handling the confidence set prediction problem. However, the validity of SCP requires the examples to be exchangeable, which is violated in the OOD setting. Empirically, we show that trivially applying SCP results in a failure to maintain the marginal coverage when the unseen target domain is different from the source domain. To address this issue, we develop a method for forming confident prediction sets in the OOD setting and theoretically prove the validity of our method. Finally, we conduct experiments on simulated data to empirically verify the correctness of our theory and the validity of our proposed method.

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。

↑