Logo Logo
Help
Contact
Switch Language to German

Hüllermeier, Eyke ORCID logoORCID: https://orcid.org/0000-0002-9944-4108; Mohr, Felix; Tornede, Alexander ORCID logoORCID: https://orcid.org/0000-0002-2415-2186 und Wever, Marcel ORCID logoORCID: https://orcid.org/0000-0001-9782-6818 (September 2021): Automated Machine Learning, Bounded Rationality, and Rational Metareasoning. ECMLPKDD Workshop on Automating Data Science (ADS2021), Virtual, 17 September 2021. [PDF, 136kB]

[thumbnail of 2109.04744v1.pdf]
Draft Version
Download (136kB)

Abstract

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.

Actions (login required)

View Item View Item