Multi-Group Learning for Hierarchical Groups
Abstract
The multi-group learning model formalizes the learning scenario in which a single predictor must generalize well on multiple, possibly overlapping subgroups of interest. We extend the study of multi-group learning to the natural case where the groups are hierarchically structured. We design an algorithm for this setting that outputs an interpretable and deterministic decision tree predictor with near-optimal sample complexity. We then conduct an empirical evaluation of our algorithm and find that it achieves attractive generalization properties on real datasets with hierarchical group structure.
Cite
Text
Deng and Hsu. "Multi-Group Learning for Hierarchical Groups." International Conference on Machine Learning, 2024.Markdown
[Deng and Hsu. "Multi-Group Learning for Hierarchical Groups." International Conference on Machine Learning, 2024.](https://mlanthology.org/icml/2024/deng2024icml-multigroup/)BibTeX
@inproceedings{deng2024icml-multigroup,
title = {{Multi-Group Learning for Hierarchical Groups}},
author = {Deng, Samuel and Hsu, Daniel},
booktitle = {International Conference on Machine Learning},
year = {2024},
pages = {10440-10487},
volume = {235},
url = {https://mlanthology.org/icml/2024/deng2024icml-multigroup/}
}