Skip to yearly menu bar Skip to main content


Poster

Learning Low-Dimensional Metrics

Blake Mason · Lalit Jain · Robert Nowak

Pacific Ballroom #44

Keywords: [ Learning Theory ] [ Similarity and Distance Learning ] [ Metric Learning ]


Abstract:

This paper investigates the theoretical foundations of metric learning, focused on three key questions that are not fully addressed in prior work: 1) we consider learning general low-dimensional (low-rank) metrics as well as sparse metrics;2) we develop upper and lower (minimax) bounds on the generalization error; 3)we quantify the sample complexity of metric learning in terms of the dimension of the feature space and the dimension/rank of the underlying metric; 4) we also bound the accuracy of the learned metric relative to the underlying true generative metric. All the results involve novel mathematical approaches to the metric learning problem, and also shed new light on the special case of ordinal embedding (aka non-metric multidimensional scaling).

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