Publications

Mohammed Rida Laraki, Geovani Rizk, Igor Colin, Albert Thomas, Yann Chevaleyre (2022). An $$backslash$alpha $-No-Regret Algorithm For Graphical Bilinear Bandits.

Geovani Rizk, Albert Thomas, Igor Colin, Rida Laraki, Yann Chevaleyre (2021). Best Arm Identification in Graphical Bilinear Bandits. International Conference on Machine Learning.

Geovani Rizk, Igor Colin, Albert Thomas, Moez Draief (2020). Refined bounds for randomized experimental design. arXiv preprint arXiv:2012.15726.

Kevin Scaman, Ludovic Dos Santos, Merwan Barlier, Igor Colin (2020). A simple and efficient smoothing method for faster optimization and local exploration. Advances in Neural Information Processing Systems.

Igor Colin (2019). An example preprint / working paper.

PDF Code Dataset Poster Video Source Document Custom Link

Igor Colin, Ludovic Dos Santos, Kevin Scaman (2019). Theoretical limits of pipeline parallel optimization and application to distributed deep learning. Advances in Neural Information Processing Systems.

Igor Colin, Albert Thomas, Moez Draief (2018). Parallel Contextual Bandits in Wireless Handover Optimization. 2018 IEEE International Conference on Data Mining Workshops (ICDMW).

Alexandre D'Aspremont, Igor Colin (2017). An Approximate Shapley-Folkman Theorem. arXiv preprint arXiv:1712.08559.

Thomas Kerdreux, Igor Colin, Alexandre D'Aspremont (2017). An approximate shapley-folkman theorem. arXiv preprint arXiv:1712.08559.

Igor Colin, Aurélien Bellet, Joseph Salmon, Stéphan Clémençon (2016). Un algorithme de Gossip pour l’optimisation décentralisée de fonctions sur les paires. Cap 2016-Conférence sur L’apprentissage automatique.