Efficient Classification for Metric Data

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.

• Type: Journal
• Year: 2010
• Where: COLT
• Authors: Lee-Ad Gottlieb, Leonid Kontorovich, Robert Krauthgamer
• Keywords: COLT 2010, General Metric Spaces, Machine Learning, Superior Classification Performance, Various Natural Metrics