SLJ
Dr. Simon Lacoste-Julien
Université de Montréal
Local AA-3339
(Until August 2016) I was a researcher at INRIA in the SIERRA project team which is part of the Computer Science Department of École Normale Supérieure in Paris. I did my PhD in Computer Science at the University of California, Berkeley under the supervision of Michael I. Jordan, and (basically) a B.Sc. Triple Honours in Mathematics, Physics and Computer Science at McGill University. I then worked with Zoubin Ghahramani as a postdoc in the Machine Learning Group of the University of Cambridge. In September 2011, I got a Research in Paris fellowship to work with Francis Bach in the SIERRA project team, and then I joined as a researcher in September 2013.

Publications

Journal papers

S. Lacoste-Julien, 2016. Convergence Rate of Frank-Wolfe for Non-Convex Objectives. arXiv preprint arXiv:1607.00345

Conference papers

G. Gidel, T. Jebara, S. Lacoste-Julien, 2016. Franke-Wolfe Algorithms for Saddle Point Problems. AISTATS 2017 – Proceedings of the 20th International Conference on Artificial Intelligence and Statistics. arXiv:1610.07797v1

A. Podosinnikova, F. Bach, S. Lacoste-Julien, 2016. Beyond CCA: Moment Matching for Multi-View Models. ICML 2016 – Proceedings of the 33rd International Conference on Machine Learning

R. Leblond, F. Pedregosa, S. Lacoste-Julien, 2016. Asaga: Asynchronous Parallel Saga. AISTATS 2017 — Proceedings of the 20th International Conference on Artificial Intelligence and Statistics

J-B Alayrac, P Bojanowski, N. Agrawal, J. Sivic, I. Laptev, S.Lacoste-Julien, 2016. Unsupervised Learning From Narrated Instruction Videos. CVPR 2016 – Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, PP. 4575-4583

A. Osokin, J-B. Alayrac, I Lukasewitz, P. K. Dokania, S. Lacoste-Julien, 2016. Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs. ICML 2016 – Proceedings of the 33rd International Conference on Machine Learning

A. Podosinnikova, F. Bach, S. Lacoste-Julien, 2015. Rethinking LDA: Moment Matching for Discrete ICA. NIPS 2015 – Advances in Neural Information Processing Systems, volume 28

R. G. Krishnan, S. Lacoste-Julien, D. Sontag, 2015. Barrier Frank-Wolfe for Marginal Inference. NIPS 2015 – Advances in Neural Information Processing Systems, volume 28.

V. Chari, S. Lacoste-Julien, I. Laptev, J. Sivic. On Pairwise Costs for Network Flow Multi-Object Tracking. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 5537-5545

S. Lacoste-Julien, F. Lindsten, F. Bach, 2015. Sequential Kernel Herding: Frank-Wolfe Optimization for Particle Filtering. AISTATS 2015 — Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, pp : 544-552

S. Lacoste-Julien, M. Jaggi, 2015. On the Global Linear Convergence of Frank-Wolfe Optimization Variants. NIPS 2015 – Advances in Neural Information Processing Systems, volume 28.

T. Hofmann, A. Lucchi, S. Lacoste-Julien, B. McWilliams. Variance Reduced Stochastic Gradient Descent with Neighbors. NIPS 2015 – Advances in Neural Information Processing Systems, volume 28.

Working papers

J-B. Alayrac, J. Sivic, I. Laptev, S. Lacoste-Julien, 2017. Joint Discovery of Object States and Manipulating Actions. arXiv:1702.02738v1