The goal of meta-learning is to train a model on a variety of learning tasks, such that it can adapt to new problems within only a few iterations. Here we propose a principled information-theoretic model that optimally partitions the underlying problem space such that specialized expert decision-makers solve the resulting sub-problems. To drive this specialization we impose the same kind of information processing constraints both on the partitioning and the expert decision-makers. We argue that this specialization leads to efficient adaptation to new tasks. To demonstrate the generality of our approach we evaluate three meta-learning domains: image classification, regression, and reinforcement learning. Download paper here Find the preprint on arxiv here
@inproceedings{hihn2019hierarchical,
title={Hierarchical expert networks for meta-learning},
author={Hihn, Heinke and Braun, Daniel Alexander},
booktitle={4th ICML Workshop on Lifelong Machine Learning},
year={2019},
organization={ICML}
}