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.
翻译:机器学习模式往往就一种分布数据进行训练,并被其他模式所应用。因此,设计一种对分布变化具有活力的模型变得非常重要。现有工作大多侧重于优化对抗性转变或干预性转变。反向方法在考虑向数据中联合分配转移时缺乏表达性,无法代表可信的转变。干预方法允许更多表达性,但提供了稳健性和无约束的转变,从而导致过度保守模式。在这项工作中,我们结合了这两种方法的互补优势,并提出了一种新的提法,即RISe,用于设计一种强有力的模型,以对抗处于对抗性和干预性转变交汇点的一套分布变化。我们使用分布性强的优化框架,以优化在监督和强化学习环境中产生的目标。从卫生保健中获取的合成和真实世界数据集的广泛实验显示了拟议方法的功效。