Skip to Main content Skip to Navigation
Conference papers

Regressive Virtual Metric Learning

Abstract : We are interested in supervised metric learning of Mahalanobis like distances. Existing approaches mainly focus on learning a new distance using similarity and dissimilarity constraints between examples. In this paper, instead of bringing closer examples of the same class and pushing far away examples of different classes we propose to move the examples with respect to virtual points. Hence, each example is brought closer to a a priori defined virtual point reducing the number of constraints to satisfy. We show that our approach admits a closed form solution which can be kernelized. We provide a theoretical analysis showing the consistency of the approach and establishing some links with other classical metric learning methods. Furthermore we propose an efficient solution to the difficult problem of selecting virtual points based in part on recent works in optimal transport. Lastly, we evaluate our approach on several state of the art datasets.
Document type :
Conference papers
Complete list of metadatas
Contributor : Michaël Perrot <>
Submitted on : Monday, October 26, 2015 - 4:55:24 PM
Last modification on : Monday, January 13, 2020 - 5:46:05 PM


  • HAL Id : hal-01220665, version 1



Michaël Perrot, Amaury Habrard. Regressive Virtual Metric Learning. Neural Information Processing Systems, Dec 2015, Montréal, Canada. ⟨hal-01220665⟩



Record views