ServiceNow Research

Alexandre Lacoste

Alexandre Lacoste

Research Scientist

Human Decision Support

Alexandre is a Research Scientist at ServiceNow Research. His main interests revolve around multi-task transfer learning using probabilistic machine learning, causality and meta-learning. In his free time, he explores how AI can help solve climate change issues.

Alexandre joined Element AI in the early 2017 as its first Research Scientist. Prior to Element AI, he worked 3 years at Google in the Research Group for building end-to-end question answering systems using deep learning. This system is currently in use by Google’s search engine to answer some of the most complex questions.

He obtained his PhD in theoretical machine learning, working with Mario Marchand and Francois Laviolette, during which he developed bridges between Bayes and PAC-Bayes theories. He obtained his Master with Douglas Eck in the former MILA where he applied machine learning to music. Finally, he studied Physics during his undergrad.

Alexandre has been playing with neural networks in his early career, in the beginning of 2000, where he self-thought himself machine learning using Christopher Bishop’s first book. He applied his knowledge to solve computer vision problems in the production line of optical components at ITF technologies.

Interests
  • Climate Change
  • Causality

Publications

Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels. Sai Rajeswar Mudumba, Pietro Mazzaglia, Tim Verbelen, Alexandre Piche, Bart Dhoedt, Aaron Courville, Alexandre Lacoste. At International Conference on Machine Learning (ICML),  2023.

PDF Cite

Choreographer: Learning and Adapting Skills in Imagination. Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt, Alexandre Lacoste, Sai Rajeswar Mudumba. At International Conference of Learning Representations (ICLR),  2023.

PDF Cite

Attention for Compositional Modularity. Oleksiy Ostapenko, Alexandre Lacoste, Pau Rodriguez. At Workshop at the Neural Information Processing Systems (NeurIPS),  2022.

PDF Cite

A General-Purpose Neural Architecture for Geospatial Systems. Alexandre Lacoste, Martin Weiss, Nasim Rahaman. At Workshop at the Neural Information Processing Systems (NeurIPS),  2022.

PDF Cite

Choreographer: Learning and Adapting Skills in Imagination . Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt, Alexandre Lacoste, Sai Rajeswar Mudumba. At Workshop at the Neural Information Processing Systems (NeurIPS),  2022.

PDF Cite

Continual Learning with self-selecting specialized modules through expansion and pruning. Oleksiy Ostapenko, Pau Rodriguez, Alexandre Lacoste, Laurent Charlin. At Montreal AI Symposium (MAIS),  2022.

Cite

Unsupervised Model-based Pre-training for Data-efficient Reinforcement Learning from Pixels. Sai Rajeswar Mudumba, Pietro Mazzaglia, Tim Verbelen, Alexandre Piche, Aaron Courville, Alexandre Lacoste. At Workshop at the International Conference on Machine Learning (ICML),  2022.

PDF Cite

Deconfounding Dynamic Treatment Regimes. David Berger, Alexandre Drouin, Alexandre Lacoste, Laurent Charlin. At SSC,  2022.

Cite

Can Active Learning Preemptively Mitigate Fairness Issues?. Frédéric Branchaud-Charron, Parmida Atighhehchian, Pau Rodriguez, Grace Abuhamad, Alexandre Lacoste. At Workshop at the International Conference on Learning Representations (ICLR),  2022.

PDF Cite Code

Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA. Sébastien Lachapelle, Pau Rodriguez, Yash Sharma, Katie Everett , Rémi Le Priol, Alexandre Lacoste, Simon Lacoste-Julien. At Causal Learning and Reasoning (CLeaR),  2022.

PDF Cite

Typing assumptions improve identification in causal discovery - theory and algorithms. Philippe Brouillard, Perouz Taslakian, Alexandre Lacoste, Sébastien Lachapelle, Alexandre Drouin. At Causal Learning and Reasoning (CLeaR),  2022.

PDF Cite Code

Tackling Climate Change with Machine Learning. David Rolnick, Priya L. Donti, Lynn H. Kaack, Kelly Kochanski, Alexandre Lacoste, Kris Sankaran, Andrew Slavin Ross, Nikola Milojevic-Dupont, Natasha Jaques, Anna Waldman-Brown, Alexandra Luccioni, Tegan Maharaj, S. Karthik Mukkavilli, Konrad P. Kording, Carla Gomes, Andrew Y. Ng, Demis Hassabis, John C. Platt, Felix Creutzig, Jennifer Chayes, Yoshua Bengio, Evan D. Sherwin. At ACM Computing Surveys,  2022.

PDF Cite

Toward Foundation Models for Earth Monitoring: Proposal for a Climate Change Benchmark. Alexandre Lacoste, Hannah Kerner, Hamed Alemohammad, Björn Lütjens, Jeremy Irvin, David Dao, Alex Chang, Mehmet Gunturkun, Alexandre Drouin, Pau Rodriguez, David Vazquez, Evan D. Sherwin. At Workshop at the Neural Information Processing Systems (NeurIPS),  2021.

PDF Cite

Typing assumptions improve identification in causal discovery - Report and comments on future directions. Philippe Brouillard, Perouz Taslakian, Alexandre Lacoste, Sébastien Lachapelle, Alexandre Drouin. At Workshop at the Neural Information Processing Systems (NeurIPS),  2021.

PDF Cite Code

Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations. Pau Rodriguez, Massimo Caccia, Alexandre Lacoste, Lee Zamparo, Issam H. Laradji, Laurent Charlin, David Vazquez. At International Conference on Computer Vision (ICCV),  2021.

PDF Cite Code

Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data. Oscar Manas, Alexandre Lacoste, Xavier Giro-i-Nieto, David Vazquez, Pau Rodriguez. At International Conference on Computer Vision (ICCV),  2021.

PDF Cite Code

Typing assumptions improve identification in causal discovery. Philippe Brouillard, Perouz Taslakian, Alexandre Lacoste, Sébastien Lachapelle, Alexandre Drouin. At Workshop at the International Conference on Machine Learning (ICML),  2021.

PDF Cite Code

Variational Causal Networks: Approximate Bayesian Inference over Causal Structures. Yashas Annadani, Jonas Rothfuss, Alexandre Lacoste, Nino Scherrer, Anirudh Goyal, Yoshua Bengio, Stefan Bauer . At Workshop at the International Conference on Machine Learning (ICML),  2021.

PDF Cite

Counting Cows: Tracking Illegal Cattle Ranching From High-Resolution Satellite Imagery. Issam H. Laradji, Pau Rodriguez, Alfredo Kalaitzis, David Vazquez, Ross Young, Ed Davey, Alexandre Lacoste. At Workshop at the Neural Information Processing Systems (NeurIPS),  2020.

PDF Cite Code

Differentiable Causal Discovery from Interventional Data. Philippe Brouillard, Sébastien Lachapelle, Alexandre Lacoste, Simon Lacoste-Julien, Alexandre Drouin. At Conference on Neural Information Processing Systems (NeurIPS),  2020.

PDF Cite Code Video

Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning. Massimo Caccia, Pau Rodriguez, Oleksiy Ostapenko, Fabrice Normandin, Min Lin, Lucas Caccia, Issam H. Laradji, Irina Rish, Alexandre Lacoste, David Vazquez, Laurent Charlin. At Conference on Neural Information Processing Systems (NeurIPS),  2020.

PDF Cite Code

Synbols: Probing Learning Algorithms with Synthetic Datasets. Alexandre Lacoste, Pau Rodriguez, Frederic Branchaud, Parmida Atighhehchian, Massimo Caccia, Issam H. Laradji, Alexandre Drouin, Matt Craddock, Laurent Charlin, David Vazquez. At Conference on Neural Information Processing Systems (NeurIPS),  2020.

PDF Cite Code

Embedding Propagation: Smoother Manifold for Few-Shot Classification. Pau Rodriguez, Issam H. Laradji, Alexandre Drouin, Alexandre Lacoste. At European Conference on Computer Vision (ECCV),  2020.

PDF Cite Code

Bayesian active learning for production, a systematic study and a reusable library. Parmida Atighhehchian, Frederic Branchaud, Alexandre Lacoste. At Workshop at the International Conference on Machine Learning (ICML),  2020.

PDF Cite Code

Estimating Carbon Emissions of Artificial Intelligence [Opinion]. Alexandra Luccioni, Alexandre Lacoste, victor schmidt. At IEEE Technology and Society Magazine,  2020.

PDF Cite Code

Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning. Massimo Caccia, Pau Rodriguez, Oleksiy Ostapenko, Fabrice Normandin, Min Lin, Lucas Caccia, Issam H. Laradji, Irina Rish, Alexandre Lacoste, David Vazquez, Laurent Charlin. At Workshop at the Conference on Computer Vision and Pattern Recognition (CVPR),  2020.

PDF Cite Code

Stochastic Neural Network with Kronecker Flow. Chin-Wei Huang, Ahmed Touati, Pascal Vincent, Gintare Karolina Dziugaite, Alexandre Lacoste, Aaron Courville. At International Conference on Artificial Intelligence and Statistics (AISTATS),  2020.

PDF Cite

Gradient-Based Neural DAG Learning with Interventions. Philippe Brouillard, Alexandre Drouin, Sébastien Lachapelle, Alexandre Lacoste, Simon Lacoste-Julien. At Workshop at the International Conference on Learning Representations (ICLR),  2020.

PDF Cite Code Video

Tackling Climate Change with Machine Learning. David Rolnick, Priya L. Donti, Lynn H. Kaack, Kelly Kochanski, Alexandre Lacoste, Kris Sankaran, Andrew Slavin Ross, Nikola Milojevic-Dupont, Natasha Jaques, Anna Waldman-Brown, Alexandra Luccioni, Tegan Maharaj, S. Karthik Mukkavilli, Konrad P. Kording, Carla Gomes, Andrew Y. Ng, Demis Hassabis, John C. Platt, Felix Creutzig, Jennifer Chayes, Yoshua Bengio, Evan D. Sherwin. At Workshop at the Neural Information Processing Systems (NeurIPS),  2019.

PDF Cite

Quantifying the Carbon Emissions of Machine Learning. Alexandre Lacoste, Alexandra Luccioni, victor schmidt, Thomas Dandres. At ArXiv,  2019.

PDF Cite Code

Hierarchical Importance Weighted Autoencoders. Chin-Wei Huang, Kris Sankaran, Eeshan Dhekane, Alexandre Lacoste, Aaron Courville. At International Conference on Machine Learning (ICML),  2019.

PDF Cite Code

Stochastic Neural Network with Kronecker Flow. Chin-Wei Huang, Ahmed Touati, Pascal Vincent, Gintare Karolina Dziugaite, Alexandre Lacoste, Aaron Courville. At Workshop at the International Conference on Machine Learning (ICML),  2019.

PDF Cite

On Difficulties of Probability Distillation. Chin-Wei Huang, Faruk Ahmed, Kundan Kumar, Alexandre Lacoste, Aaron Courville. At International Conference on Learning Representations (ICLR),  2019.

PDF Cite

Improving Explorability in Variational Inference with Annealed Variational Objectives. Chin-Wei Huang, Shawn Tan, Alexandre Lacoste, Aaron Courville. At Conference on Neural Information Processing Systems (NeurIPS),  2018.

PDF Cite Code

TADAM: Task dependent adaptive metric for improved few-shot learning. Boris N. Oreshkin, Pau Rodriguez, Alexandre Lacoste. At Conference on Neural Information Processing Systems (NeurIPS),  2018.

PDF Cite Code

Synbols: Probing Learning Algorithms with Synthetic Datasets. Alexandre Lacoste, Pau Rodriguez, Frédéric Branchaud-Charron, Parmida Atighhehchian, Massimo Caccia, Issam H. Laradji, Alexandre Drouin, Matt Craddock, Laurent Charlin, David Vazquez. At Montreal AI Symposium (MAIS),  2018.

PDF Cite Code

Neural Autoregressive Flows. Chin-Wei Huang, David Krueger, Alexandre Lacoste, Aaron Courville. At International Conference on Machine Learning (ICML),  2018.

PDF Cite Code

Learning Heuristics for the TSP by Policy Gradient. Michel Deudon, Pierre Cournut, Alexandre Lacoste, Yossiri Adulyasak, Louis-Martin Rousseau. At International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research,  2018.

PDF Cite Code

Bayesian Hypernetworks. David Krueger, Chin-Wei Huang, Riashat Islam, Ryan Turner, Alexandre Lacoste, Aaron Courville. At Workshop at the Neural Information Processing Systems (NeurIPS),  2017.

PDF Cite

Deep Prior. Alexandre Lacoste, Thomas Boquet, Negar Rostamzadeh, Boris N. Oreshkin, Wonchang Chung, David Krueger. At Workshop at the Neural Information Processing Systems (NeurIPS),  2017.

PDF Cite

Accurate Supervised and Semi-Supervised Machine Reading for Long Documents. Daniel Hewlett, Llion Jones, Alexandre Lacoste, Izzeddin Gur. At Conference on Empirical Methods in Natural Language Processing (EMNLP),  2017.

PDF Cite

Coarse-to-Fine Question Answering for Long Documents. Eunsol Choi, Daniel Hewlett, Jakob Uszkoreit, Illia Polosukhin, Alexandre Lacoste, Jonathan Berant. At Annual Meeting of the Association for Computational Linguistics (ACL),  2016.

PDF Cite