Igor Colin ☕️
Igor Colin

Associate Professor

About Me

I am an associate professor at ESIEE Paris, Université Gustave Eiffel. Previously, I was a research engineer in the S2A team at Télécom Paris and a researcher in the Noah’s Ark team at Huawei. During 2017, I was a postdoctoral researcher at INRIA, SIERRA under the supervision of Alexandre d’Aspremont. From 2013 to 2016, I was a Ph.D. student, co-advised by Stephan Clémençon and Joseph Salmon. In 2013, I graduated the Master MVA (machine learning and computer vision) at ENS Cachan and obtained the engineering degree of École des Ponts ParisTech.

Download CV
Interests
  • Decentralized Learning
  • Bandits
  • Convex/Non-Convex Optimization
  • Graphs
Education
  • PhD Machine Learning

    LTCI, Télécom ParisTech

  • MRes Machine Learning and Computer Vision

    École Normale Supérieure, Cachan

  • MSc Applied Maths and Computer Science

    École des Ponts ParisTech

Recent Publications
(2026). Decentralized Ranking Aggregation via Gossip: Convergence and Robustness. Advances in Neural Information Processing Systems (NeurIPS 2026, to appear).
(2026). On Gossip Algorithms for Machine Learning with Pairwise Objectives. Transactions on Machine Learning Research.
(2026). Fast and Efficient Asynchronous Gossip Algorithm for Robust and Non-Smooth Convex Decentralized Learning. arXiv preprint arXiv:2601.20571 (under review).
(2025). Robust Distributed Estimation: Extending Gossip Algorithms to Ranking and Trimmed Means. Advances in Neural Information Processing Systems (NeurIPS 2025).
(2025). Adaptive Sample Sharing for Multi Agent Linear Bandits. In ICML.