Timezone: »

Bayesian Active Meta-Learning under Prior Misspecification
Sabina Sloman · Ayush Bharti · Samuel Kaski
Event URL: https://openreview.net/forum?id=hd1Lte6eUc »

We study a setting in which an active meta-learner aims to separate the idiosyncracies of a particular task environment from information that will transfer between task environments. In a Bayesian setting, this is accomplished by leveraging a prior distribution on the amount of transferable and task-specific information an observation will yield, inducing a large dependency on this prior when data is scarce or environments change frequently. However, a misspecified prior can lead to bias in the inferences made on the basis of the resulting posterior --- i.e., to the acquisition of non-transferable information. For an active meta-learner, this poses a dilemma: should they seek transferable information on the basis of their possibly misspecified prior beliefs, or task-specific information that enables better identification of the current task environment? Using the framework of Bayesian experimental design, we develop a novel diagnostic to detect the risk of non-transferable information acquisition, and leverage this diagnostic to propose an intuitive yet principled way to navigate the meta-learning dilemma --- namely, seek task-specific information when there is risk of non-transferable information acquisition, and transferable information otherwise. We provide a proof-of-concept of our approach in the context of an experiment with synthetic participants.

Author Information

Sabina Sloman (University of Manchester)
Ayush Bharti (Aalto University)
Samuel Kaski (Aalto University and University of Manchester)

More from the Same Authors