Simon Lacoste-Julien’s research focuses on machine learning, i.e. how to program a computer to learn from data and solve useful tasks. His primary research goal is to develop and analyze machine learning techniques which can exploit at large scale the rich structure of data in interdisciplinary applications such as natural language processing, information retrieval, computer vision and computational biology. To this end, he combines tools from optimization, statistics and computer science and he particularly enjoys working at the interface between domains. He is best known for his contributions to the field of structured prediction (classification problems where the outputs are structured objects like sequences or graphs), to large scale optimization (incremental gradient method and Frank-Wolfe optimization), and to the combination of generative and discriminative methods.
NSERC Discovery Grant , 2017.
Google Focused Research Award , 2016.
Wolfson College Junior Research Fellowship, University of Cambridge , 2009-2011.
UC Berkeley College of Engineering Graduate Student Prize , 2008.
A. Osokin, F. Bach and S. Lacoste-Julien (2017), "On Structured Prediction Theory with Calibrated Convex Surrogate Losses", NIPS.
S. Lacoste-Julien and M. Jaggi (2015), "On the Global Linear Convergence of Frank-Wolfe Optimization Variants", NIPS.
A. Defazio, F. Bach and S. Lacoste-Julien (2014), "SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives", NIPS.
S. Lacoste-Julien, M. Jaggi, M. Schmidt and P. Pletscher (2013), "Block-Coordinate Frank-Wolfe Optimization for Structural SVMs", ICML.
S. Lacoste-Julien, F. Huszár, and Z. Ghahramani (2011), "Approximate Inference for the Loss-Calibrated Bayesian", AISTATS.
Fellow Learning in Machines & Brains
Université de MontréalDepartment of Computer Science and Operations Research (DIRO)
Ph.D., Computer Science UC Berkeley
B.Sc. Joint Honours Math & Physics, Joint Honours Math & CS McGill University
No Assets Found
Sorry, we did not find any assets matching these filters.