Skip to yearly menu bar Skip to main content


Poster

Active Nearest-Neighbor Learning in Metric Spaces

Aryeh Kontorovich · Sivan Sabato · Ruth Urner

Area 5+6+7+8 #147

Keywords: [ Learning Theory ] [ (Other) Classification ] [ Active Learning ]


Abstract:

We propose a pool-based non-parametric active learning algorithm for general metric spaces, called MArgin Regularized Metric Active Nearest Neighbor (MARMANN), which outputs a nearest-neighbor classifier. We give prediction error guarantees that depend on the noisy-margin properties of the input sample, and are competitive with those obtained by previously proposed passive learners. We prove that the label complexity of MARMANN is significantly lower than that of any passive learner with similar error guarantees. Our algorithm is based on a generalized sample compression scheme and a new label-efficient active model-selection procedure.

Live content is unavailable. Log in and register to view live content