TY - GEN

T1 - Efficient classification for metric data

AU - Gottlieb, Lee Ad

AU - Kontorovich, Aryeh

AU - Krauthgamer, Robert

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Recent advances in large-margin classification of data residing in general metric spaces (rather than Hilbert spaces) enable classification under various natural metrics, such as edit and earthmover distance. The general framework developed for this purpose by von Luxburg and Bousquet [JMLR, 2004] left open the question of computational efficiency and providing direct bounds on classification error. We design a new algorithm for classification in general metric spaces, whose runtime and accuracy depend on the doubling dimension of the data points. It thus achieves superior classification performance in many common scenarios. The algorithmic core of our approach is an approximate (rather than exact) solution to the classical problems of Lipschitz extension and of Nearest Neighbor Search. The algorithm's generalization performance is established via the fat-shattering dimension of Lipschitz classifiers.

AB - Recent advances in large-margin classification of data residing in general metric spaces (rather than Hilbert spaces) enable classification under various natural metrics, such as edit and earthmover distance. The general framework developed for this purpose by von Luxburg and Bousquet [JMLR, 2004] left open the question of computational efficiency and providing direct bounds on classification error. We design a new algorithm for classification in general metric spaces, whose runtime and accuracy depend on the doubling dimension of the data points. It thus achieves superior classification performance in many common scenarios. The algorithmic core of our approach is an approximate (rather than exact) solution to the classical problems of Lipschitz extension and of Nearest Neighbor Search. The algorithm's generalization performance is established via the fat-shattering dimension of Lipschitz classifiers.

UR - http://www.scopus.com/inward/record.url?scp=78149346758&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:78149346758

SN - 9780982252925

T3 - COLT 2010 - The 23rd Conference on Learning Theory

SP - 433

EP - 440

BT - COLT 2010 - The 23rd Conference on Learning Theory

T2 - 23rd Conference on Learning Theory, COLT 2010

Y2 - 27 June 2010 through 29 June 2010

ER -