A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution. However, this assumption is violated in almost all practical applications: machine learning systems are regularly tested under distribution shift, due to temporal correlations, particular end users, or other factors. In this work, we consider the setting where the training data are structured into groups and test time shifts correspond to changes in the group distribution. Prior work has approached this problem by attempting to be robust to all possible test time distributions, which may degrade average performance. In contrast, we propose to use ideas from meta-learning to learn models that are adaptable, such that they can adapt to shift at test time using a batch of unlabeled test points. We acquire such models by learning to adapt to training batches sampled according to different distributions, which simulate structural shifts that may occur at test time. Our primary contribution is to introduce the framework of adaptive risk minimization (ARM), a formalization of this setting that lends itself to meta-learning. We develop meta-learning methods for solving the ARM problem, and compared to a variety of prior methods, these methods provide substantial gains on image classification problems in the presence of shift.

中文翻译：

---

自适应风险最小化：解决群体转移的元学习方法

大多数机器学习算法的一个基本假设是训练和测试数据来自相同的底层分布。然而，几乎所有实际应用都违反了这一假设：由于时间相关性、特定最终用户或其他因素，机器学习系统在分布偏移下定期进行测试。在这项工作中，我们考虑了训练数据被组织成组并且测试时间偏移对应于组分布的变化的设置。先前的工作通过尝试对所有可能的测试时间分布保持鲁棒性来解决这个问题，这可能会降低平均性能。相比之下，我们建议使用元学习的思想来学习适应性强的模型，这样它们就可以使用一批未标记的测试点来适应测试时的转变。我们通过学习适应根据不同分布采样的训练批次来获得此类模型，这模拟了测试时可能发生的结构变化。我们的主要贡献是引入了自适应风险最小化 (ARM) 框架，这是一种适用于元学习的设置形式化。我们开发了用于解决 ARM 问题的元学习方法，与各种先前的方法相比，这些方法在存在移位的情况下在图像分类问题上提供了实质性的收益。