Model Characterization with Inductive Orientation Vectors

Kerria Pang-Naylor, Eric Chen, Eric Chen, George Montañez

2025

Abstract

As models rise in complexity, black-box evaluation and interpretation methods become critical. We introduce estimation methods for characterizing model-theoretic quantities such as algorithm flexibility, responsiveness to changes in training data, and ability to specialize. These methods are applicable to any black-box classification algorithm. Past theoretical work has shown how such qualities affect probability of task success, generalization, and tendency to overfit. We perform metric estimations of interpretable models across hyperparameters and corroborate the metrics’ behavior with known algorithm heuristics. This work presents a general model-agnostic interpretability tool.

Paper Citation

in Harvard Style

Pang-Naylor K., Chen E. and Montañez G. (2025). Model Characterization with Inductive Orientation Vectors. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 670-681. DOI: 10.5220/0013304400003890

in Bibtex Style

@conference{icaart25,
author={Kerria Pang-Naylor and Eric Chen and George Montañez},
title={Model Characterization with Inductive Orientation Vectors},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={670-681},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013304400003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Model Characterization with Inductive Orientation Vectors
SN - 978-989-758-737-5
AU - Pang-Naylor K.
AU - Chen E.
AU - Montañez G.
PY - 2025
SP - 670
EP - 681
DO - 10.5220/0013304400003890
PB - SciTePress