Scholar
Michaël Perrot
Google Scholar ID: zk1LyHAAAAAJ
Researcher INRIA
Citations & Impact
Citations
406
H-index
9
i10-index
9
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Published several papers, including 'Near-Optimal Comparison Based Clustering' (NeurIPS, 2020), 'Too Relaxed to be Fair' (ICML, 2020), 'Foundations of Comparison-Based Hierarchical Clustering' (NeurIPS, 2019), 'Boosting for Comparison-Based Learning' (IJCAI, 2019, Distinguished Paper Award), 'Mapping Estimation for Discrete Optimal Transport' (NeurIPS, 2016).
Research Experience
- Worked as a post-doc researcher in the Statistical Learning Theory research group led by Ulrike von Luxburg, part of both Eberhard Karls Universität Tübingen and Max Planck Institute for Intelligent Systems, from April 2017 to September 2019, mainly studying the problem of learning from ordinal data, generally termed as Comparison-based Learning, and got interested in the problem of Fair Machine Learning; worked as a post-doc researcher in the Data Intelligence Team in the Laboratoire Hubert Curien, studying the problem of Fair Machine Learning in the presence of Imbalanced Data, from March 2020 to September 2020; since October 2020, working as a researcher in the Magnet Team in the Centre INRIA Lille - Nord Europe.
Education
- PhD obtained in December 2016 from the University of Saint-Etienne, France, under the supervision of Amaury Habrard, focusing on Metric Learning, specifically about Learning Metrics with a Controlled Behaviour.
Background
- Research Interests: Fair Machine Learning, Comparison-based Learning, Statistical Learning Theory, Machine Learning. Biography: Michaël Perrot is a researcher in machine learning.
Miscellany
- Contact: michael.perrot@inria.fr
Co-authors