Robustness and Generalization for Metric Learning

Abstract : Metric learning has attracted a lot of interest over the last decade, but the generalization ability of such methods has not been thoroughly studied. In this paper, we introduce an adaptation of the notion of algorithmic robustness (previously introduced by Xu and Mannor) that can be used to derive generalization bounds for metric learning. We further show that a weak notion of robustness is in fact a necessary and sufficient condition for a metric learning algorithm to generalize. To illustrate the applicability of the proposed framework, we derive generalization results for a large family of existing metric learning algorithms, including some sparse formulations that are not covered by previous results.
Document type :
Journal articles
Complete list of metadatas

Cited literature [33 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01075370
Contributor : Amaury Habrard <>
Submitted on : Tuesday, October 21, 2014 - 2:52:26 PM
Last modification on : Tuesday, September 10, 2019 - 11:32:07 AM
Long-term archiving on : Thursday, January 22, 2015 - 10:31:13 AM

File

paper.pdf
Files produced by the author(s)

Identifiers

Citation

Aurélien Bellet, Amaury Habrard. Robustness and Generalization for Metric Learning. Neurocomputing, Elsevier, 2015, pp.16. ⟨10.1016/j.neucom.2014.09.044⟩. ⟨hal-01075370⟩

Share

Metrics

Record views

151

Files downloads

172