How Local Should a Learning Method Be?

We consider the question of why modern machine learning methods like support vector machines outperform earlier nonparametric techniques like kNN. Our approach investigates the locality of learning methods, i.e., the tendency to focus mainly on the close-by part of the training set when constructing a new guess at a particular location. We show that, on the one hand, we can expect all consistent learning methods to be local in some sense; hence if we consider consistency a desirable property then a degree of locality is unavoidable. On the other hand, we also claim that earlier methods like k-NN are local in a more strict manner which implies performance limitations. Thus, we argue that a degree of locality is necessary but that this should not be overdone. Support vector machines and related techniques strike a good balance in this matter, which we suggest may partially explain their good performance in practice.

• Type: Conference
• Year: 2008
• Where: COLT
• Authors: Alon Zakai, Yaacov Ritov
• Keywords: COLT 2008, Learning Methods, Machine Learning, Machine Learning Methods, Support Vector Machines