Home
About me

Hadrien Hendrikx

 

Briefly

I am a researcher (Chargé de Recherche) in the Thoth team at Inria Grenoble, a French public research institute. From October 2021 to December 2022, I was a post-doc in the MLO team from EPFL, working with Martin Jaggi. Before that (2018-2021), I was a Ph.D. student in the SIERRA and DYOGENE (now ARGO) teams from Inria Paris, which are also part of the Computer Science Department of Ecole Normale Supérieure. I was also part of the MSR-INRIA joint centre. I worked under the supervision of Francis Bach and Laurent Massoulié on 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

  • Physical address: Inria, 655 Av. de l'Europe, 38330 Montbonnot-Saint-Martin

  • E-mail: hadrien [dot] hendrikx [at] inria [dot] fr

Openings

I have funding for either a post-doc or an engineer on ML methods for studying underground fauna, with a focus on generalization capabilities, i.e., how to efficiently predict for new scanners in previously unseen soil types (no annotations, but potentially plenty of data already). More info and the actual offer coming soon.

More generally, feel free to contact me if you're interested in ML for ecology.

Research interests

I am broadly interested in optimization for machine learning, regardless of the flavor: stochastic, accelerated, non-euclidean… My two main research directions in this area are distributed optimization (and in particular challenges tied to robustness, privacy and personalization), and mirror descent methods (and in particular how to develop a consistent stochastic theory).

I currently focus most of my energy on developing projects at the interface between machine learning and other scientific disciplines, and in particular ecology. I am for instance part of the CASCA project with the Eco&Sol lab, where we leverage modern computer vision to better understand underground fauna. I also work in close collaboration with the Laboratoire d'Ecologie Alpine (LECA) in Grenoble.

Please contact me for discussions and potential collaborations!

Teaching

  • 2024 - 2025: Teacher, Numerical Optimization, M1 Applied Mathematics, Université Grenoble Alpes

  • 2024 - 2025: Teacher (part-time), Generalizations Properties of Machine Learning Algorithms, M2 Mathématiques de l'aléatoire, Orsay.

  • 2023 - 2024: Teacher, Numerical Optimization, M1 Applied Mathematics, Université Grenoble Alpes

  • 2023 - 2024: Teacher (part-time), Generalizations Properties of Machine Learning Algorithms, M2 Mathématiques de l'aléatoire, Orsay.

  • 2019 - 2020: Teaching assistant, Advanced Algorithms (L3 Informatique), University Paris Descartes

  • 2018 - 2019: Teaching assistant, Advanced Algorithms (L3 Informatique), Logic (L1 Informatique) University Paris Descartes

Reviewing

  • Conferences: ICML 2019 (Top 5%), NeurIPS 2019 (Top 400), ICML 2020 (Top 33%), NeurIPS 2020 (Top 10%), AISTATS 2021, ICML 2021, NeurIPS 2021, AISTATS 2022, ICML 2022 (Top 10%), NeurIPS 2022, AISTATS 2023 (Top 10%), ICML 2023, AISTATS 2023, AISTATS 2024, ICML 2024, NeurIPS 2024.

  • Journals: Mathematical Programming, IEEE Transactions on Signal Processing, Automatica, SIOPT, JMLR

Supervision

Current:

  • Renaud Gaucher: PhD Student, Byzantine-robust optimization. Co-supervised with Aymeric Dieuleveut

  • Loukas Duqué: PhD Student, ML for wireless communications. Co-supervised with Jean-Marie Gorce and Florence Forbes

  • Hippolyte Verninas: PhD Student, Dimensionality reduction for large-scale physics simulation. Co-supervised with Thomas Moreau

Former:

  • Géraud Ilinca: Master Student, Benchmarking PCA for large-scale physics simulation. Co-supervised with Thomas Moreau

  • Morgan Scalabrino: Master Student, Invertebrates detection and classification

  • Manuela Giraldo Obando: Master student, attacks in distributed learning

  • Mohamed Bacar Abdoulandhum: Master Student, co-supervised with Léa Lugassy (PADV)

  • Daniel Morales Broton: Master Student.

  • Abdellah El Mrini: Master Student

  • Rustem Islamov: Master Student

  • Mathieu Even: PhD student at INRIA Paris with Laurent Massoulié

Publications and preprints

  • R. Gaucher, A. Dieuleveut, H. Hendrikx, From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similarity.
    [arXiv:2602.03329], preprint, 2026.

  • T. Guilmeau, H. Hendrikx, F. Forbes, Convergence of projected stochastic natural gradient variational inference: Balancing speed, computational effort, and accuracy.
    To appear. International Conference on Artificial Intelligence and Statistics (AISTATS), 2026

  • R. Gaucher, A. Dieuleveut, H. Hendrikx, Byzantine-Robust Gossip: Insights from a Dual Approach.
    [arXiv:2405.03449], Transactions on Machine Learning Research (TMLR), 2026.

  • S. Cerna, S. Si-Moussi, W. Thuiller, H. Hendrikx, V. Miele, BotaCLIP: Contrastive Learning for Botany-Aware Representation of Earth Observation Data.
    [arXiv:2511.21194], preprint, 2025

  • R. Gaucher, A. Dieuleveut, H. Hendrikx, Unified breakdown analysis for byzantine robust gossip.
    [arXiv:2410.10418], International Conference on Machine Learning (ICML), 2025.

  • M. Even, H. Hendrikx, L. Massoulié. Decentralized Optimization with Heterogeneous Delays: a Continuous-Time Approach.
    [arXiv:2106.03585], IEE Transactions on Automatic Control, 2025.

  • H. Hendrikx, Investigating Variance Definitions for Stochastic Mirror Descent with Relative Smoothness.
    [arXiv:2404.12213], preprint, 2024.

  • D. Morales-Brotons, T. Vogels, H. Hendrikx, Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits,
    [arXiv:2411.18704], Transactions on Machine Learning Research (TMLR), 2024.

  • H. Hendrikx, P. Mangold, A. Bellet. The Relative Gaussian Mechanism and its Application to Private Gradient Descent.
    [arXiv:2308.15250], International Conference on Artificial Intelligence and Statistics (AISTATS), 2024.

  • A. Koloskova*, H. Hendrikx*, S. Stich. Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees.
    [arXiv:2305.01588], International Conference on Machine Learning (ICML), 2023.

  • T. Vogels*, H. Hendrikx*, M. Jaggi. Beyond spectral gap (extended): the role of the topology in decentralized learning.
    [arXiv:2301.02151], Journal of Machine Learning Research (JMLR), 2023.

  • H. Hendrikx. A principled framework for the design and analysis of token algorithms.
    [arXiv:2205.15015, video], International Conference on Artificial Intelligence and Statistics (AISTATS), 2023.

  • T. Vogels*, H. Hendrikx*, M. Jaggi. Beyond spectral gap: the role of the topology in decentralized learning.
    [arXiv:2206.03093, video], Advances in Neural Information Processing Systems (NeurIPS), 2022.

  • H. Hendrikx. Accelerated Methods for Distributed Optimization.
    [HAL link], PhD Thesis, PSL Research university, 2021.

  • M. Even, R. Berthier, F. Bach, N. Flammarion, P. Gaillard, H. Hendrikx, L. Massoulié, A. Taylor A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip.
    [arXiv:2106.07644, video], Advances in Neural Information Processing Systems (NeurIPS), 2021. Oral Presentation. Outstanding paper award.

  • H. Hendrikx, F. Bach, L. Massoulié. An Optimal Algorithm for Decentralized Finite Sum Optimization.
    [arXiv:2005.10675], SIAM Journal on Optimization, 2021.

  • R. Dragomir*, M. Even*, H. Hendrikx*. Fast Stochastic Bregman Gradient Methods: Sharp Analysis and Variance Reduction.
    [arXiv:2104.09813], International Conference on Machine Learning (ICML), 2021.

  • H. Hendrikx, F. Bach, L. Massoulié. Dual-Free Stochastic Decentralized Optimization with Variance Reduction.
    [arXiv:2006.14384], Advances in Neural Information Processing Systems (NeurIPS), 2020.

  • H. Hendrikx, L. Xiao, S. Bubeck, F. Bach, L. Massoulié. Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization.
    [arXiv:2002.10726, video], International Conference on Machine Learning (ICML), 2020.

  • A. Bellet, R. Guerraoui, H. Hendrikx. Who started this rumor? Quantifying the natural differential privacy guarantees of gossip protocols.
    [arXiv:1902.07138], International Symposium on DIStributed Computing (DISC), 2020.

  • H. Hendrikx, F. Bach, L. Massoulié. An Accelerated Decentralized Stochastic Proximal Algorithm for Finite Sums.
    [arXiv:1905.11394], Advances in Neural Information Processing Systems (NeurIPS), 2019.

  • H. Hendrikx, F. Bach, L. Massoulié. Accelerated Decentralized Optimization with Local Updates for Smooth and Strongly Convex Objectives.
    [arXiv:1810.02660], International Conference on Artificial Intelligence and Statistics (AISTATS), 2019.

  • EM. El-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. Spotlight presentation.

  • 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.

* denotes equal contribution