Authors:
Pedro Sandoval Segura
1
;
2
;
Julius Lauw
1
;
Daniel Bashir
1
;
Kinjal Shah
1
;
Sonia Sehra
1
;
Dominique Macias
1
and
George Montañez
1
Affiliations:
1
AMISTAD Lab, Department of Computer Science, Harvey Mudd College, Claremont, CA, U.S.A.
;
2
Department of Computer Science, University of Maryland, College Park, MD, U.S.A.
Keyword(s):
Machine Learning, Model Complexity, Algorithm Capacity, VC Dimension, Label Recorder.
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.