arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.01205cs.LGstat.ML
收藏

局部可解释性的学习理论视角

A Learning Theoretic Perspective on Local Explainability

University of Washington(华盛顿大学);Carnegie Mellon University(卡内基梅隆大学);Determined AI(Determined人工智能公司)

Jeffrey Li, Vaishnavh Nagarajan, Gregory Plumb, Ameet Talwalkar

摘要:

在本文中,我们通过局部近似解释的视角来探索可解释的机器学习和学习理论之间的联系。首先,我们解决了传统的性能泛化问题,并使用局部可解释性的概念来约束模型的测试时准确性。其次,我们探讨了新的问题的解释推广,这是一个重要的关注一类不断增长的有限样本为基础的局部近似解释。最后,我们验证了我们的理论结果的经验,并表明它们反映了什么可以在实践中看到。

英文摘要:

In this paper, we explore connections between interpretable machine learning and learning theory through the lens of local approximation explanations. First, we tackle the traditional problem of performance generalization and bound the test-time accuracy of a model using a notion of how locally explainable it is. Second, we explore the novel problem of explanation generalization which is an important concern for a growing class of finite sample-based local approximation explanations. Finally, we validate our theoretical results empirically and show that they reflect what can be seen in practice.

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。

↑