Geometric Mean Metric Learning


Pourya Zadeh, Reshad Hosseini, Suvrit Sra ;
Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:2464-2471, 2016.


We revisit the task of learning a Euclidean metric from data. We approach this problem from first principles and formulate it as a surprisingly simple optimization problem. Indeed, our formulation even admits a closed form solution. This solution possesses several very attractive properties: (i) an innate geometric appeal through the Riemannian geometry of positive definite matrices; (ii) ease of interpretability; and (iii) computational speed several orders of magnitude faster than the widely used LMNN and ITML methods. Furthermore, on standard benchmark datasets, our closed-form solution consistently attains higher classification accuracy.

Related Material