Service interruption on Monday 11 July from 12:30 to 13:00: all the sites of the CCSD (HAL, Epiciences, SciencesConf, AureHAL) will be inaccessible (network hardware connection).
Skip to Main content Skip to Navigation
Conference papers

Algorithmic Robustness for Semi-Supervised (ε, γ, τ )-Good Metric Learning

Abstract : The importance of metrics in machine learning has attracted a growing interest for distance and similarity learning, and especially the Mahalanobis distance. However, it is worth noting that this research field lacks theoretical guarantees that can be expected on the generalization capacity of the classifier associated to a learned metric. The theoreti- cal framework of (ε,γ,τ)-good similarity functions [1] has been one of the first attempts to draw a link between the properties of a similarity function and those of a linear classifier making use of it. In this paper, we extend this theory to a method where the metric and the separator are jointly learned in a semi-supervised way, setting that has not been explored before. We furthermore provide a generalization bound for the associated classifier based on the algorithmic robustness framework. The behavior of our method is illustrated via some experimental results.
Document type :
Conference papers
Complete list of metadata
Contributor : Amaury Habrard Connect in order to contact the contributor
Submitted on : Monday, November 2, 2015 - 3:51:32 PM
Last modification on : Tuesday, July 5, 2022 - 10:10:00 AM


  • HAL Id : hal-01223411, version 1



Nicolae Irina, Marc Sebban, Amaury Habrard, Eric Gaussier, Massih-Reza Amini. Algorithmic Robustness for Semi-Supervised (ε, γ, τ )-Good Metric Learning. International Conference on Neural Information Processing ICONIP, Nov 2015, Istanbul, Turkey. pp.10. ⟨hal-01223411⟩



Record views