arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2102.12353cs.LGstat.ML
收藏

非线性不变风险最小化:一种因果方法

Nonlinear Invariant Risk Minimization: A Causal Approach

University of Cambridge(剑桥大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);University of Toronto(多伦多大学);Vector Institute(向量研究所);Alan Turing Institute(艾伦·图灵研究所)

Chaochao Lu, Yuhuai Wu, Jośe Miguel Hernández-Lobato, Bernhard Schölkopf

摘要:

由于虚假的相关性,机器学习系统通常无法推广到分布与训练时使用的分布不同的环境。以前的工作解决这个问题,无论是显式或隐式,试图找到一个数据表示,具有不变的关系与目标。这是通过利用一组不同的训练环境来减少虚假特征的影响并构建一个不变的预测器来实现的。然而,这些方法只有在数据表示和分类器都来自线性模型类时才有泛化保证。我们提出了不变因果表示学习(iCaRL),这是一种在非线性环境中实现分布外(OOD)泛化的方法(即,非线性表示和非线性分类器)。它建立在一个实际和一般的假设之上:数据表示的先验(即,编码数据的一组潜在变量)属于一般指数族分布。在此基础上,我们表明,它是可能的,以确定简单的转换的数据表示。我们还证明了目标的所有直接原因可以被完全发现,这进一步使我们能够在非线性设置中获得泛化保证。在合成数据集和真实数据集上的大量实验表明,我们的方法优于各种基线方法。最后,在讨论中,我们进一步探讨了上述假设,并提出了一个更普遍的假设,称为不可知论假设:存在一组隐藏的因果因素影响输入和结果。不可知论假说可以提供机器学习的统一观点。更重要的是,它可以激发一个新的方向,探索一个通用的理论,识别隐藏的因果因素,这是关键,使面向对象的泛化保证。

英文摘要:

Due to spurious correlations, machine learning systems often fail to generalize to environments whose distributions differ from the ones used at training time. Prior work addressing this, either explicitly or implicitly, attempted to find a data representation that has an invariant relationship with the target. This is done by leveraging a diverse set of training environments to reduce the effect of spurious features and build an invariant predictor. However, these methods have generalization guarantees only when both data representation and classifiers come from a linear model class. We propose invariant Causal Representation Learning (iCaRL), an approach that enables out-of-distribution (OOD) generalization in the nonlinear setting (i.e., nonlinear representations and nonlinear classifiers). It builds upon a practical and general assumption: the prior over the data representation (i.e., a set of latent variables encoding the data) given the target and the environment belongs to general exponential family distributions. Based on this, we show that it is possible to identify the data representation up to simple transformations. We also prove that all direct causes of the target can be fully discovered, which further enables us to obtain generalization guarantees in the nonlinear setting. Extensive experiments on both synthetic and real-world datasets show that our approach outperforms a variety of baseline methods. Finally, in the discussion, we further explore the aforementioned assumption and propose a more general hypothesis, called the Agnostic Hypothesis: there exist a set of hidden causal factors affecting both inputs and outcomes. The Agnostic Hypothesis can provide a unifying view of machine learning. More importantly, it can inspire a new direction to explore a general theory for identifying hidden causal factors, which is key to enabling the OOD generalization guarantees.

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。

↑