Hadrien Hendrikx

 

Briefly

Since September 2018, I am a Ph.D. student in the SIERRA and DYOGENE teams, which are part of the Computer Science Department of Ecole Normale Supérieure and are also joint teams between CNRS and INRIA. I am also part of the MSR-INRIA joint centre. I work under the supervision of Francis Bach and Laurent Massoulié on asynchronous algorithms for decentralized optimization.

Prior to that, I graduated from Ecole Polytechnique in 2016 and got a master degree from EPFL in Computer Science (Master en Informatique) in 2018. During my master, I had the chance to work as a Research Assistant in the DCL lab under the supervision of Rachid Guerraoui and in close collaboration with Aurélien Bellet.

Contact

Research interests

I am broadly interested in any problem related to making many entities work together efficiently without a central authority. At the moment, I mainly focus on decentralized methods for distributed optimization, and in particular:

  • Accelerated methods for convex optimization

  • Asynchronous algorithms

  • Gossip (peer-to-peer) algorithms

  • Privacy issues in decentralized learning

I used to study the impact of interruptions on learning in a multi-agents system.

Teaching

2018 - 2019: Teaching assistant, Advanced Algorithms, L3 Informatique, University Paris Descartes

Talks

  • Invited talk, Aligned AI workshop (NIPS 2017)

  • Spotlight presentation, Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning, NIPS 2017

Publications

  • H. Hendrikx, L. Massoulié, F. Bach. Accelerated Decentralized Optimization with Local Updates for Smooth and Strongly Convex Objectives.
    [arXiv:1810.02660], arXiv Preprint, 2018.

  • EME Mhamdi, R Guerraoui, H Hendrikx, A Maurer. Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning.
    [arXiv:1704.02882], Advances in Neural Information Processing Systems (NIPS), 2017.

  • H. Hendrikx, M. Nuñez del Prado Cortez. Towards a route detection method based on detail call records.
    [IEEE Xplore 7885725], In Computational Intelligence (LA-CCI), 2016 IEEE Latin American Conference on (pp. 1-6). IEEE., 2016.