A recent line of work has focused on training machine learning (ML) models in the performative setting, i.e. when the data distribution reacts to the deployed model. The goal in this setting is to learn a model which both induces a favorable data distribution and performs well on the induced distribution, thereby minimizing the test loss. Previous work on finding an optimal model assumes that the data distribution immediately adapts to the deployed model. In practice, however, this may not be the case, as the population may take time to adapt to the model. In many applications, the data distribution depends on both the currently deployed ML model and on the "state" that the population was in before the model was deployed. In this work, we propose a new algorithm, Stateful Performative Gradient Descent (Stateful PerfGD), for minimizing the performative loss even in the presence of these effects. We provide theoretical guarantees for the convergence of Stateful PerfGD. Our experiments confirm that Stateful PerfGD substantially outperforms previous state-of-the-art methods.
翻译:最近的一项工作侧重于在性能环境下对机器学习模式的培训,即当数据分发模式对部署模式作出反应时。这一环境的目标是学习一种模式,既能促进有利的数据分发,又在诱发分布方面表现良好,从而最大限度地减少试验损失。以前关于寻找最佳模式的工作假定数据分发立即适应部署模式。但在实际中,情况可能并非如此,因为人口可能要花时间适应模型。在许多应用中,数据分发取决于目前部署的ML模式和在模型部署之前人口处于“状态”的模式。在这项工作中,我们提出了一种新的算法,即“状态性作用梯子(状态梯子)”,以尽可能减少即使存在这些效应的情况下的性损失。我们为国有化的PerfGD的趋同提供了理论保证。我们的实验证实,国家式的PerfGD在实质上超越了先前的“状态”方法。