Rémi Leblond

Ph.D. Candidate
Laboratoire d'informatique de l'Ecole Normale Supérieure

I'm a third year Ph.D. student at INRIA in the Sierra team under the supervision of Simon Lacoste-Julien. I'm interested in very large scale optimization for new complex machine learning models. My current focus is on structured prediction using neural networks and parallel and distributed algorithms.

After graduating from Ecole Polytechnique and Corps des Mines (French MPA), I worked in the Big Data field for three years, as a Data Scientist at SpotRight in the US (2011-2012) and as a Data Engineer at the Ministry of Defense (2013-2015).


Machine learning and optimization

SEARNN: Training RNNs with global-local losses.
Rémi Leblond*, Jean-Baptiste Alayrac*, Anton Osokin and Simon Lacoste-Julien.
* Equal contribution
ICLR 2018
Presented at DeepStruct 2017 (ICML workshop)
Presented at the MILA DLSS 2017

Breaking the nonsmooth barrier: a scalable parallel method for composite optimization.
Fabian Pedregosa, Rémi Leblond and Simon Lacoste-Julien.
NIPS 2017 (Spotlight)
Presented at EUROPT 2017

Asaga: Asynchronous parallel Saga.
Rémi Leblond, Fabian Pedregosa and Simon Lacoste-Julien.
Presented at OPT2016 (9th NIPS Workshop on Optimization for Machine Learning)

Probabilistic processes on graphs

Cutoff phenomenon for the simple exclusion process on the complete graph.
Hubert Lacoin, Rémi Leblond.
ALEA: Latin American Journal of Probability and Mathematical Statistics, 2011


Rémi Leblond
INRIA Paris, Office C408
2 Rue Simone Iff
75012 Paris
See LinkedIn profile Send an email Github repository