The Labeling Distribution Matrix (LDM): A Tool for Estimating Machine Learning Algorithm Capacity

Pedro Sandoval Segura, Pedro Sandoval Segura, Julius Lauw, Daniel Bashir, Kinjal Shah, Sonia Sehra, Dominique Macias, George Montañez

2020

Abstract

Algorithm performance in supervised learning is a combination of memorization, generalization, and luck. By estimating how much information an algorithm can memorize from a dataset, we can set a lower bound on the amount of performance due to other factors such as generalization and luck. With this goal in mind, we introduce the Labeling Distribution Matrix (LDM) as a tool for estimating the capacity of learning algorithms. The method attempts to characterize the diversity of possible outputs by an algorithm for different training datasets, using this to measure algorithm flexibility and responsiveness to data. We test the method on several supervised learning algorithms, and find that while the results are not conclusive, the LDM does allow us to gain potentially valuable insight into the prediction behavior of algorithms. We also introduce the Label Recorder as an additional tool for estimating algorithm capacity, with more promising initial results.

Download


Paper Citation


in Harvard Style

Segura P., Lauw J., Bashir D., Shah K., Sehra S., Macias D. and Montañez G. (2020). The Labeling Distribution Matrix (LDM): A Tool for Estimating Machine Learning Algorithm Capacity. In Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-395-7, pages 980-986. DOI: 10.5220/0009178209800986


in Bibtex Style

@conference{icaart20,
author={Pedro Segura and Julius Lauw and Daniel Bashir and Kinjal Shah and Sonia Sehra and Dominique Macias and George Montañez},
title={The Labeling Distribution Matrix (LDM): A Tool for Estimating Machine Learning Algorithm Capacity},
booktitle={Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2020},
pages={980-986},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009178209800986},
isbn={978-989-758-395-7},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - The Labeling Distribution Matrix (LDM): A Tool for Estimating Machine Learning Algorithm Capacity
SN - 978-989-758-395-7
AU - Segura P.
AU - Lauw J.
AU - Bashir D.
AU - Shah K.
AU - Sehra S.
AU - Macias D.
AU - Montañez G.
PY - 2020
SP - 980
EP - 986
DO - 10.5220/0009178209800986