Latest news

  • May 24

    New paper on decentralized ML and privacy

    Fast and Differentially Private Algorithms for Decentralized Collaborative Machine Learning (arXiv:1705.08435). pdf

  • Jan 25

    One paper accepted to AISTATS 2017

    Decentralized Collaborative Learning of Personalized Models over Networks (AISTATS 2017). pdf

  • Jan 16

    New paper on speech recognition

    Kernel Approximation Methods for Speech Recognition (arXiv:1701.03577). pdf

  • Oct 10

    One paper accepted to NIPS 2016 workshop

    A Decentralized and Robust Protocol for Private Averaging over Highly Distributed Data (NIPS 2016 workshop Private Multi-Party Machine Learning).

  • Aug 17

    Co-organization of a workshop at NIPS 2016

    I am co-organizing the NIPS 2016 workshop on Private Multi-Party Machine Learning. Check out the CFP!

  • Aug 12

    One paper accepted to NIPS 2016

    On Graph Reconstruction via Empirical Risk Minimization: Fast Learning Rates and Scalability (NIPS 2016). pdf

Short bio

I am a tenured researcher at Inria, where I am part of the Magnet Team (MAchine learninG in information NETworks). I am also affiliated with CRIStAL (UMR CNRS 9189), a research center of the University of Lille.

Prior to joining Inria, I was a postdoctoral researcher at the University of Southern California (working with Fei Sha) and then at Télécom ParisTech (working with Stéphan Clémençon). I obtained my Ph.D. from the University of Saint-Etienne in 2012 under the supervision of Marc Sebban and Amaury Habrard.

You can find more information in my CV or on my LinkedIn profile.

Research interests

My main line of research is in statistical machine learning. I am particularly interested in designing large-scale learning algorithms which allow a good trade-off between computational complexity (or other resources, such as communication cost) and statistical performance.

My current research focus includes:

  • similarity and distance metric learning
  • large-scale machine learning
  • distributed / decentralized algorithms
  • optimization for machine learning
  • graph-based learning
  • statistical learning theory
  • applications to NLP, speech recognition and computer vision