I am a machine learning researcher in S2A team at Télécom Paris. Previously, I was a research in Noah's Ark research 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.

My resume.

Research Interests

Research Papers

Parallel Contextual Bandits in Wireless Handover Optimization
Igor Colin, Albert Thomas and Moez Draief,
In ICDM 2018, DaMNet.

Stable Bounds on the Duality Gap of Finite Sum Minimization Problems
Thomas Kerdreux, Igor Colin and Alexandre d'Aspremont.

Decentralized Topic Modelling with Latent Dirichlet Allocation
Igor Colin and Christophe Dupuy,
In NIPS 2016, Workshop on Private Multi‑Party Machine Learning.

Adapting Machine Learning Techniques to U-statistics
Igor Colin,
Ph.D. Thesis.

Scaling-up Empirical Risk Minimization: Optimization of Incomplete U-statistics
Stephan Clémençon, Aurélien Bellet and Igor Colin,
In JMLR.

Gossip Dual Averaging for Decentralized Optimization of Pairwise Functions
Igor Colin, Aurélien Bellet, Joseph Salmon and Stephan Clémençon,
In ICML 2016.

Extending Gossip Algorithms to Distributed Estimation of U-Statistics
Igor Colin, Aurélien Bellet, Joseph Salmon and Stephan Clémençon,
In NIPS 2015, selected for spotlight.

Learning information cascades in social networks
Igor Colin,
Master's Thesis, 2013.

Teaching

Ph.D. Students

Miscellaneous