Portrait of Alexandre Drouin

Alexandre Drouin

Associate Industry Member
Adjunct professor, Université Laval, Department of Electrical Engineering and Computer Engineering
Research Scientist, ServiceNow

Biography

Alexandre Drouin is a research scientist at ServiceNow Research in Montréal, and an adjunct professor of computer science at Université Laval. He also leads ServiceNow’s Human Decision Support research program, which explores the use of machine learning for decision-making in complex dynamic environments.

Droiun’s main research interest is causal decision-making under uncertainty, where the goal is to answer questions of causal nature (interventions, counterfactual), while accounting for sources of uncertainty, such as ambiguity in causal structures and unmeasured variables. He is also interested in probabilistic time series forecasting and its use in foreseeing the long-term effect of actions. His PhD in computer science from Université Laval was on machine learning algorithms for biomarker discovery in large genomic datasets and their application to the global problem of antibiotic resistance.

Current Students

Research Intern - Université de Montréal
Principal supervisor :
PhD - Université de Montréal
Principal supervisor :
PhD - Université Laval
Principal supervisor :

Publications

In Search of Robust Measures of Generalization
Brady Neal
Nitarshan Rajkumar
Ethan Caballero
Linbo Wang
Daniel M. Roy
One of the principal scientific challenges in deep learning is explaining generalization, i.e., why the particular way the community now tra… (see more)ins networks to achieve small training error also leads to small error on held-out data from the same population. It is widely appreciated that some worst-case theories -- such as those based on the VC dimension of the class of predictors induced by modern neural network architectures -- are unable to explain empirical performance. A large volume of work aims to close this gap, primarily by developing bounds on generalization error, optimization error, and excess risk. When evaluated empirically, however, most of these bounds are numerically vacuous. Focusing on generalization bounds, this work addresses the question of how to evaluate such bounds empirically. Jiang et al. (2020) recently described a large-scale empirical study aimed at uncovering potential causal relationships between bounds/measures and generalization. Building on their study, we highlight where their proposed methods can obscure failures and successes of generalization measures in explaining generalization. We argue that generalization measures should instead be evaluated within the framework of distributional robustness.
Synbols: Probing Learning Algorithms with Synthetic Datasets
Alexandre Lacoste
Pau Rodr'iguez
Frédéric Branchaud-charron
Parmida Atighehchian
Massimo Caccia
Issam Hadj Laradji
Matt P. Craddock
David Vazquez