Classifiers in High Dimensional Hilbert Metrics

TL;DR

This paper introduces efficient algorithms for classifying points in high-dimensional Hilbert polygonal metrics, including SVM and nearest neighbor methods, with polynomial runtime guarantees, advancing geometric machine learning techniques.

Contribution

It presents the first polynomial-time algorithms for large-margin SVM and related classification tasks in the Hilbert metric, improving over previous exponential-time methods.

Findings

Polynomial-time algorithm for large-margin SVM in Hilbert metric

Efficient algorithms for soft-margin SVM and nearest neighbor classification

Significant runtime improvements over previous methods

Abstract

Classifying points in high dimensional spaces is a fundamental geometric problem in machine learning. In this paper, we address classifying points in the $d$-dimensional Hilbert polygonal metric. The Hilbert metric is a generalization of the Cayley-Klein hyperbolic distance to arbitrary convex bodies and has a diverse range of applications in machine learning and convex geometry. We first present an efficient LP-based algorithm in the metric for the large-margin SVM problem. Our algorithm runs in time polynomial to the number of points, bounding facets, and dimension. This is a significant improvement on previous works, which either provide no theoretical guarantees on running time, or suffer from exponential runtime. We also consider the closely related Funk metric. We also present efficient algorithms for the soft-margin SVM problem and for nearest neighbor-based classification in the Hilbert metric.