Olivier Bousquet
Olivier received his PhD in Machine Learning from Ecole Polytechnique, France in 2002. He was then a researcher at the Max Planck Institute in Tuebingen, working on Machine Learning and in particular Statistical Learning Theory and Kernel Methods. In 2004 he joined a startup company where he lead a research team and developed ML software for predicting manufacturing quality.
Olivier joined Google Zurich in 2007 and contributed to many aspects of the search engine, in particular leading an engineering team working on Language Understanding and the Knowledge Graph. In 2016, he joined the Research team and is now working on Deep Learning and Language Understanding, leading the Brain teams in Zurich and Paris.
His research interests include Learning with limited supervision (Semi-supervised or Unsupervised), AutoML (automation of Deep Learning), Learning of world representations and world knowledge.
Research Areas
Authored Publications
Sort By
Google
Fine-Grained Distribution-Dependent Learning Curves
Jonathan Shafer
Shay Moran
Steve Hanneke
Proceedings of Thirty Sixth Conference on Learning Theory (COLT), PMLR 195:5890-5924, 2023. (2023)
Differentially-Private Bayes Consistency
Aryeh Kontorovich
Shay Moran
Menachem Sadigurschi
Archive, Archive, Archive
What Do Neural Networks Learn When Trained With Random Labels?
Hartmut Maennel
Robert J. N. Baldock
Sylvain Gelly
NeurIPS 2020
Evaluating Generative Models using Divergence Frontiers
Josip Djolonga
Marco Cuturi
Sylvain Gelly
International Conference on Artificial Intelligence and Statistics (2020)
Measuring Compositional Generalization: A Comprehensive Method on Realistic Data
Nathanael Schärli
Nathan Scales
Hylke Buisman
Daniel Furrer
Nikola Momchev
Danila Sinopalnikov
Lukasz Stafiniak
Tibor Tihon
Dmitry Tsarkov
Marc van Zee
ICLR (2020)
When can unlabeled data improve the learning rate?
Christina Göpfert
Shai Ben-David
Sylvain Gelly
Ruth Urner
COLT 2019
Practical and Consistent Estimation of f-Divergences
Paul Rubenstein
Josip Djolonga
Carlos Riquelme
Submission to Neurips 2019. (2019) (to appear)
