Michaël Perrot

Biography

I obtained my PhD in December 2016 from the University of Saint-Etienne, France. During my thesis I mainly studied Metric Learning, more precisely it was about Learning Metrics with a Controlled Behaviour. I did it under the supervision of Amaury Habrard in the Laboratoire Hubert Curien.

Since April 2017 I work as a post-doc researcher in the Statistical Learning Theory research group led by Ulrike von Luxburg. This group is part of both the Eberhard Karls Universität Tübingen and the Max Planck Institute for Intelligent Systems. I study the problem of learning from ordinal data, generally termed as Comparison-based Learning.

I am currently looking for a new post-doc position! You can download my CV here.

We address the classical problem of hierarchical clustering, but in a framework where one does not have access to a representation of …

Debarghya Ghoshdastidar, Michaël Perrot, Ulrike von Luxburg

In NeurIPS, 2019

Preprint PDF Code Poster

We consider the problem of classification in a comparison-based setting: given a set of objects, we only have access to triplet …

Michaël Perrot, Ulrike von Luxburg

In IJCAI, Distinguished Paper Award, 2019

Preprint PDF Code

We are interested in the computation of the transport map of an Optimal Transport problem. Most of the computational approaches of …

Michaël Perrot, Nicolas Courty, Rémi Flamary, Amaury Habrard

In NeurIPS, 2016

PDF Code Poster

We are interested in supervised metric learning of Mahalanobis like distances. Existing approaches mainly focus on learning a new …

Michaël Perrot, Amaury Habrard

In NeurIPS, 2015

PDF Code Poster

We consider the problem of transferring some a priori knowledge in the context of supervised metric learning approaches. While this …

Michaël Perrot, Amaury Habrard

In ICML, 2015

PDF Poster Slides