Automated Machine Learning, Bounded Rationality, and Rational Metareasoning
This work provides a theoretical perspective on AutoML, but it is incremental as it applies an existing concept from economics and AI to a specific domain without introducing new methods or results.
The paper frames automated machine learning (AutoML) as a bounded rationality problem, where an AutoML tool is viewed as an agent that must optimally allocate limited computational resources to train a model and search for a suitable ML pipeline.
The notion of bounded rationality originated from the insight that perfectly rational behavior cannot be realized by agents with limited cognitive or computational resources. Research on bounded rationality, mainly initiated by Herbert Simon, has a longstanding tradition in economics and the social sciences, but also plays a major role in modern AI and intelligent agent design. Taking actions under bounded resources requires an agent to reflect on how to use these resources in an optimal way - hence, to reason and make decisions on a meta-level. In this paper, we will look at automated machine learning (AutoML) and related problems from the perspective of bounded rationality, essentially viewing an AutoML tool as an agent that has to train a model on a given set of data, and the search for a good way of doing so (a suitable "ML pipeline") as deliberation on a meta-level.