Robustness and Generalization for Metric Learning

by   Aurélien Bellet, et al.
Jean Monnet University

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.


page 1

page 2

page 3

page 4


Supervised Metric Learning with Generalization Guarantees

The crucial importance of metrics in machine learning algorithms has led...

Sparse Compositional Metric Learning

We propose a new approach for metric learning by framing it as learning ...

Metric Learning via Maximizing the Lipschitz Margin Ratio

In this paper, we propose the Lipschitz margin ratio and a new metric le...

Provably Robust Metric Learning

Metric learning is an important family of algorithms for classification ...

Generalization Bounds for Metric and Similarity Learning

Recently, metric learning and similarity learning have attracted a large...

A Metric Learning Reality Check

Deep metric learning papers from the past four years have consistently c...

Dimension Free Generalization Bounds for Non Linear Metric Learning

In this work we study generalization guarantees for the metric learning ...

Please sign up or login with your details

Forgot password? Click here to reset