Unsupervised Ground Metric Learning

TL;DR

This paper explores unsupervised metric learning by analyzing algorithms for optimal transport cost matrices, proposing a convergent stochastic algorithm, and investigating alternative distances like Mahalanobis and graph Laplacian-based methods.

Contribution

It introduces a linear convergence proof for a stochastic algorithm in unsupervised metric learning and compares different distance measures including OT, Mahalanobis, and graph Laplacians.

Findings

Proposed a stochastic algorithm with linear convergence.

Demonstrated the applicability of Mahalanobis and graph Laplacian distances.

Analyzed the algorithmic and modeling aspects of unsupervised metric learning.

Abstract

Data classification without access to labeled samples remains a challenging problem. It usually depends on an appropriately chosen distance between features, a topic addressed in metric learning. Recently, Huizing, Cantini and Peyr\'e proposed to simultaneously learn optimal transport (OT) cost matrices between samples and features of the dataset. This leads to the task of finding positive eigenvectors of a certain nonlinear function that maps cost matrices to OT distances. Having this basic idea in mind, we consider both the algorithmic and the modeling part of unsupervised metric learning. First, we examine appropriate algorithms and their convergence. In particular, we propose to use the stochastic random function iteration algorithm and prove that it converges linearly for our setting, although our operators are not paracontractive as it was required for convergence so far. Second, we ask the natural question if the OT distance can be replaced by other distances. We show how Mahalanobis-like distances fit into our considerations. Further, we examine an approach via graph Laplacians. In contrast to the previous settings, we have just to deal with linear functions in the wanted matrices here, so that simple algorithms from linear algebra can be applied.