Nicolas Usunier

Research Scientist

I joined Facebook as a Research Scientist in March 2015. I received my PhD in Machine Learning from Université Pierre et Marie Curie, in Paris, in 2006. I was Associate Profesor there until 2012, when I joined Université de Technologie de Compiègne, in France, with a chair position from the “CNRS-Higher Education Chairs” program. My research interests are learning theory, learning to rank, and learning with multiples objectives.


Machine learning theory and algorithms, information retrieval, text analysis

Latest Publications

NeurIPS - December 5, 2020

On ranking via sorting by estimated expected utility

Clèment Calauzènes, Nicolas Usunier

ECCV - August 23, 2020

End-to-End Object Detection with Transformers

Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, Sergey Zagoruyko

July 14, 2020

Growing Action Spaces

Gregory Farquhar, Laura Gustafson, Zeming Lin, Shimon Whiteson, Nicolas Usunier, Gabriel Synnaeve

NeurIPS - October 18, 2019

A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning

Nicolas Carion, Gabriel Synnaeve, Alessandro Lazaric, Nicolas Usunier

ICLR - May 6, 2019

Value Propagation Networks

Nantas Nardelli, Gabriel Synnaeve, Zeming Lin, Pushmeet Kohli, Philip H.S. Torr, Nicolas Usunier

Reinforcement Learning under Partial Observability Workshop at NeurIPS 2018 - December 3, 2018

High-Level Strategy Selection under Partial Observability in StarCraft: Brood War

Jonas Gehring, Da Ju, Vegard Mella, Daniel Gant, Nicolas Usunier, Gabriel Synnaeve

NeurIPS - December 3, 2018

Forward Modeling for Partial Observation Strategy Games – A StarCraft Defogger

Gabriel Synnaeve, Zeming Lin, Jonas Gehring, Dan Gant, Vegard Mella, Vasil Khalidov, Nicolas Carion, Nicolas Usunier

NIPS 2018 - October 26, 2018

SING: Symbol-to-Instrument Neural Generator

Alexandre Défossez, Neil Zeghidour, Nicolas Usunier, Leon Bottou, Francis Bach

ICML 2018 - June 18, 2018

Canonical Tensor Decomposition for Knowledge Base Completion

Timothée Lacroix, Nicolas Usunier, Guillaume Obozinski

ICASSP 2018 - April 15, 2018

Learning Filterbanks from Raw Speech for Phone Recognition

Neil Zeghidour, Nicolas Usunier, Iasonas Kokkinos, Thomas Schatz, Gabriel Synnaeve, Emmanuel Dupoux

NIPS 2017 - December 4, 2017

Fader Networks: Manipulating Images by Sliding Attributes

Guillaume Lample, Neil Zeghidour, Nicolas Usunier, Antoine Bordes, Ludovic Denoyer, Marc'Aurelio Ranzato

ICCV 2017 - October 22, 2017

Dense and Low-Rank Gaussian CRFs using Deep Embeddings

Siddhartha Chandra, Nicolas Usunier, Iasonas Kokkinos

ICLR 2017 - April 24, 2017

Improving Neural Language Models with a Continuous Cache

Edouard Grave, Armand Joulin, Nicolas Usunier

ICLR 2017 - April 24, 2017

Episodic Exploration for Deep Deterministic Policies for StarCraft Micro-Management

Nicolas Usunier, Gabriel Synnaeve, Zeming Lin, Soumith Chintala

September 8, 2016

Joint Learning of Speaker and Phonetic Similarities with Siamese Networks

Neil Zeghidour, Gabriel Synnaeve, Nicolas Usunier, Emmanuel Dupoux

JAIR - June 20, 2016

Combining Two and Three-Way Embeddings Models for Link Prediction in Knowledge Bases

Alberto Garcia-Duran, Antoine Bordes, Nicolas Usunier, Yves Grandvalet

ArXiv - June 22, 2015

Large-Scale Simple Question Answering with Memory Networks

Antoine Bordes, Nicolas Usunier, Sumit Chopra, Jason Weston