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 2301.05975stat.MEcs.LG
收藏

基于LASSO的广义不变匹配性质

Generalized Invariant Matching Property via LASSO

University of Utah(犹他大学)

Kang Du, Yu Xiang

摘要:

分布变化下的学习是一项具有挑战性的任务。一种原则性的方法是通过结构因果模型来利用不变性原理。然而,当响应被干预时,不变性原则被违反,使其成为一个困难的设置。在最近的一项工作中,不变匹配属性已经被开发出来,以阐明这种情况下,并显示出有前途的性能。在这项工作中,通过制定一个高维的问题与内在的稀疏性,我们推广了不变的匹配属性的一个重要的设置时,只有目标是干预。我们提出了一个更强大的和计算效率的算法,利用Lasso的变体,改进现有的算法。

英文摘要:

Learning under distribution shifts is a challenging task. One principled approach is to exploit the invariance principle via the structural causal models. However, the invariance principle is violated when the response is intervened, making it a difficult setting. In a recent work, the invariant matching property has been developed to shed light on this scenario and shows promising performance. In this work, by formulating a high-dimensional problem with intrinsic sparsity, we generalize the invariant matching property for an important setting when only the target is intervened. We propose a more robust and computation-efficient algorithm by leveraging a variant of Lasso, improving upon the existing algorithms.

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。

↑