arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.15933cs.LGstat.ML
收藏

在对抗性和干预性转变下学习

Learning Under Adversarial and Interventional Shifts

New York University(纽约大学);Harvard University(哈佛大学)

Harvineet Singh, Shalmali Joshi, Finale Doshi-Velez, Himabindu Lakkaraju

摘要:

机器学习模型通常在来自一个分布的数据上进行训练,并部署在其他分布上。因此,设计对分布偏移具有鲁棒性的模型变得非常重要。大多数现有的工作集中在优化对抗性转变或干预性转变。对抗性方法在表示合理的变化时缺乏表现力,因为它们考虑了数据中联合分布的变化。干预方法允许更多的表达,但提供了鲁棒性无限的变化,导致过于保守的模型。在这项工作中,我们结合了这两种方法的互补优势,并提出了一个新的配方,RISe,设计强大的模型对一组分布偏移,在交叉的对抗和干预的转变。我们采用分布式鲁棒优化框架来优化监督和强化学习设置中的最终目标。对来自医疗保健的合成和真实世界数据集的广泛实验证明了所提出的方法的有效性。

英文摘要:

Machine learning models are often trained on data from one distribution and deployed on others. So it becomes important to design models that are robust to distribution shifts. Most of the existing work focuses on optimizing for either adversarial shifts or interventional shifts. Adversarial methods lack expressivity in representing plausible shifts as they consider shifts to joint distributions in the data. Interventional methods allow more expressivity but provide robustness to unbounded shifts, resulting in overly conservative models. In this work, we combine the complementary strengths of the two approaches and propose a new formulation, RISe, for designing robust models against a set of distribution shifts that are at the intersection of adversarial and interventional shifts. We employ the distributionally robust optimization framework to optimize the resulting objective in both supervised and reinforcement learning settings. Extensive experimentation with synthetic and real world datasets from healthcare demonstrate the efficacy of the proposed approach.

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。

↑