TY - GEN

T1 - Quantifying accuracy of learning via sample width

AU - Anthony, Martin

AU - Ratsaby, Joel

PY - 2013/10/15

Y1 - 2013/10/15

N2 - In a recent paper, the authors introduced the notion of sample width for binary classifiers defined on the set of real numbers. It was shown that the performance of such classifiers could be quantified in terms of this sample width. This paper considers how to adapt the idea of sample width so that it can be applied in cases where the classifiers are defined on some finite metric space. We discuss how to employ a greedy set-covering heuristic to bound generalization error. Then, by relating the learning problem to one involving certain graph-theoretic parameters, we obtain generalization error bounds that depend on the sample width and on measures of 'density' of the underlying metric space.

AB - In a recent paper, the authors introduced the notion of sample width for binary classifiers defined on the set of real numbers. It was shown that the performance of such classifiers could be quantified in terms of this sample width. This paper considers how to adapt the idea of sample width so that it can be applied in cases where the classifiers are defined on some finite metric space. We discuss how to employ a greedy set-covering heuristic to bound generalization error. Then, by relating the learning problem to one involving certain graph-theoretic parameters, we obtain generalization error bounds that depend on the sample width and on measures of 'density' of the underlying metric space.

UR - http://www.scopus.com/inward/record.url?scp=84885227586&partnerID=8YFLogxK

U2 - https://doi.org/10.1109/FOCI.2013.6602459

DO - https://doi.org/10.1109/FOCI.2013.6602459

M3 - Conference contribution

SN - 9781467359016

T3 - Proceedings of the 2013 IEEE Symposium on Foundations of Computational Intelligence, FOCI 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

SP - 84

EP - 90

BT - Proceedings of the 2013 IEEE Symposium on Foundations of Computational Intelligence, FOCI 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

T2 - 2013 IEEE Symposium on Foundations of Computational Intelligence, FOCI 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

Y2 - 16 April 2013 through 19 April 2013

ER -