Multidimensional Shape Constraints
Abstract
We propose new multi-input shape constraints across four intuitive categories: complements, diminishers, dominance, and unimodality constraints. We show these shape constraints can be checked and even enforced when training machine-learned models for linear models, generalized additive models, and the nonlinear function class of multi-layer lattice models. Real-world experiments illustrate how the different shape constraints can be used to increase explainability and improve regularization, especially for non-IID train-test distribution shift.
Cite
Text
Gupta et al. "Multidimensional Shape Constraints." International Conference on Machine Learning, 2020.Markdown
[Gupta et al. "Multidimensional Shape Constraints." International Conference on Machine Learning, 2020.](https://mlanthology.org/icml/2020/gupta2020icml-multidimensional/)BibTeX
@inproceedings{gupta2020icml-multidimensional,
title = {{Multidimensional Shape Constraints}},
author = {Gupta, Maya and Louidor, Erez and Mangylov, Oleksandr and Morioka, Nobu and Narayan, Taman and Zhao, Sen},
booktitle = {International Conference on Machine Learning},
year = {2020},
pages = {3918-3928},
volume = {119},
url = {https://mlanthology.org/icml/2020/gupta2020icml-multidimensional/}
}