Hugo Larochelle

Mila > About Mila > Team > Hugo Larochelle
Core Industry Member
Hugo Larochelle
Adjunct Professor, Université de Montréal, Google
Hugo Larochelle

I am the lead of the Google Brain team in Montreal, adjunct professor at Université de Montréal and a Canada CIFAR Chair. My research focuses on the study and development of deep learning algorithms.

For additional information on me and my research, consider the following links:



Learning a Universal Template for Few-shot Dataset Generalization.
Eleni Triantafillou, Hugo Larochelle, Richard S. Zemel and Vincent Dumoulin
arXiv: Learning
Learning Flexible Classifiers with Shot-CONditional Episodic (SCONE) Training
Eleni Triantafillou, Vincent Dumoulin, Hugo Larochelle and Richard Zemel
(venue unknown)
Dependency Structure Discovery from Interventions
Nan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal, Stefan Bauer, Bernhard Schölkopf, Michael Curtis Mozer, Hugo Larochelle, Christopher Pal and Yoshua Bengio
(venue unknown)
Uniform Priors for Data-Efficient Transfer
Samarth Sinha, Karsten Roth, Anirudh Goyal, Marzyeh Ghassemi, Hugo Larochelle and Animesh Garg
A Universal Representation Transformer Layer for Few-Shot Image Classification
Lu Liu, William L. Hamilton, Guodong Long, Jing Jiang and Hugo Larochelle


Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark.
Vincent Dumoulin, Neil Houlsby, Utku Evci, Xiaohua Zhai, Ross Goroshin, Sylvain Gelly and Hugo Larochelle
arXiv preprint arXiv:2104.02638


Interpretable Multi-Modal Hate Speech Detection.
Prashanth Vijayaraghavan, Hugo Larochelle and Deb Roy
arXiv preprint arXiv:2103.01616


Self-Supervised Equivariant Scene Synthesis from Video
Cinjon Resnick, Or Litany, Cosmas Heiß, Hugo Larochelle, Joan Bruna and Kyunghyun Cho
arXiv preprint arXiv:2102.00863


An Effective Anti-Aliasing Approach for Residual Networks.
Cristina Vasconcelos, Hugo Larochelle, Vincent Dumoulin, Nicolas Le Roux and Ross Goroshin
arXiv preprint arXiv:2011.10675
Learned Equivariant Rendering without Transformation Supervision.
Cinjon Resnick, Or Litany, Hugo Larochelle, Joan Bruna and Kyunghyun Cho
arXiv preprint arXiv:2011.05787


Revisiting Fundamentals of Experience Replay
William Fedus, Prajit Ramachandran, Rishabh Agarwal, Yoshua Bengio, Hugo Larochelle, Mark Rowland and Will Dabney
Small-GAN: Speeding up GAN Training using Core-Sets
Samrath Sinha, Han Zhang, Anirudh Goyal, Yoshua Bengio, Hugo Larochelle and Augustus Odena


Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin, Pascal Lamblin, Utku Evci, Kelvin Xu, Ross Goroshin, Carles Gelada, Kevin Swersky, Pierre-Antoine Manzagol and Hugo Larochelle
Language GANs Falling Short
Massimo Caccia, Lucas Caccia, William Fedus, Hugo Larochelle, Joelle Pineau and Laurent Charlin
sistemas e métodos para realizar otimização bayesiana
Hugo Larochelle, Kevin Swersky, Richard Zemel, Roland Jasper Snoek and Ryan P Adams
(venue unknown)
Algorithmic Improvements for Deep Reinforcement Learning Applied to Interactive Fiction.
Vishal Jain, William Fedus, Hugo Larochelle, Doina Precup and Marc G. Bellemare


Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)
Joelle Pineau, Philippe Vincent-Lamarre, Koustuv Sinha, Vincent Larivière, Alina Beygelzimer, Florence d'Alché-Buc, Emily B. Fox and Hugo Larochelle
arXiv preprint arXiv:2003.12206
On-the-Fly Adaptation of Source Code Models using Meta-Learning
Disha Shrivastava, Hugo Larochelle and Daniel Tarlow
arXiv preprint arXiv:2003.11768
Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling
Tong Che, Ruixiang Zhang, Jascha Sohl-Dickstein, Hugo Larochelle, Liam Paull, Yuan Cao and Yoshua Bengio
DIBS: Diversity inducing Information Bottleneck in Model Ensembles.
Samarth Sinha, Homanga Bharadhwaj, Anirudh Goyal, Hugo Larochelle, Animesh Garg and Florian Shkurti
arXiv preprint arXiv:2003.04514
Curriculum By Texture.
Samarth Sinha, Animesh Garg and Hugo Larochelle
(venue unknown)
The Hanabi Challenge: A New Frontier for AI Research
Nolan Bard, Jakob N. Foerster, Sarath Chandar, Neil Burch, Marc Lanctot, H. Francis Song, Emilio Parisotto, Vincent Dumoulin, Subhodeep Moitra, Edward Hughes, Iain Dunning, Shibl Mourad, Hugo Larochelle, Marc G. Bellemare and Michael Bowling
Artificial Intelligence


On Catastrophic Interference in Atari 2600 Games.
William Fedus, Dibya Ghosh, John D. Martin, Marc G. Bellemare, Yoshua Bengio and Hugo Larochelle
arXiv preprint arXiv:2002.12499


Acquiring and Predicting Multidimensional Diffusion (MUDI) Data: An Open Challenge
Marco Pizzolato, Marco Palombo, Elisenda Bonet-Carne, Chantal M. W. Tax, Francesco Grussu, Andrada Ianus, Fabian Bogusz, Tomasz Pieciak, Lipeng Ning, Hugo Larochelle, Maxime Descoteaux, Maxime Chamberland, Stefano B. Blumberg, Thomy Mertzanidou, Daniel C. Alexander, Maryam Afzali, Santiago Aja-Fernández, Derek K. Jones, Carl-Fredrik Westin, Yogesh Rathi... (10 more)
(venue unknown)
Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
David Bieber, Charles Sutton, Hugo Larochelle and Daniel Tarlow
Few-Shot Learning
(venue unknown)
Curriculum By Smoothing
Samarth Sinha, Animesh Garg and Hugo Larochelle
Learning Graph Structure With A Finite-State Automaton Layer
Daniel D. Johnson, Hugo Larochelle and Daniel Tarlow


Are Few-shot Learning Benchmarks Too Simple ?
(venue unknown)


A RAD approach to deep mixture models
Laurent Dinh, Jascha Sohl-Dickstein, Razvan Pascanu and Hugo Larochelle


Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time
arXiv preprint arXiv:1902.08605
Centroid Networks for Few-Shot Clustering and Unsupervised Few-Shot Classification.
(venue unknown)
Hyperbolic Discounting and Learning over Multiple Horizons
William Fedus, Carles Gelada, Yoshua Bengio, Marc G. Bellemare and Hugo Larochelle
arXiv preprint arXiv:1902.06865


InfoBot: Transfer and Exploration via the Information Bottleneck
Anirudh Goyal, Riashat Islam, Daniel Strouse, Zafarali Ahmed, Matthew Botvinick, Hugo Larochelle, Yoshua Bengio and Sergey Levine
arXiv preprint arXiv:1901.10902
InfoBot: Structured Exploration in ReinforcementLearning Using Information Bottleneck
Anirudh Goyal, Riashat Islam, Daniel Strouse, Zafarali Ahmed, Matthew Botvinick, Hugo Larochelle, Yoshua Bengio and Sergey Levine
(venue unknown)
InfoBot: Transfer and Exploration via the Information Bottleneck
Anirudh Goyal, Riashat Islam, Daniel Strouse, Zafarali Ahmed, Hugo Larochelle, Matthew Botvinick, Yoshua Bengio and Sergey Levine
ICLR 2019


Blindfold Baselines for Embodied QA.
Ankesh Anand, Eugene Belilovsky, Kyle Kastner, Hugo Larochelle and Aaron C. Courville
arXiv: Computer Vision and Pattern Recognition


Recall Traces: Backtracking Models for Efficient Reinforcement Learning
Anirudh Goyal, Philemon Brakel, William Fedus, Soumye Singhal, Timothy P. Lillicrap, Sergey Levine, Hugo Larochelle and Yoshua Bengio


Disentangling the independently controllable factors of variation by interacting with the world
Valentin Thomas, Emmanuel Bengio, William Fedus, Jules Pondard, Philippe Beaudoin, Hugo Larochelle, Joelle Pineau, Doina Precup and Yoshua Bengio
arXiv preprint arXiv:1802.09484


HoME: a Household Multimodal Environment.
Simon Brodeur, Ethan Perez, Ankesh Anand, Florian Golemo, Luca Celotti, Florian Strub, Jean Rouat, Hugo Larochelle and Aaron C. Courville
ICLR 2018

Publications collected and formatted using Paperoni

array(6) { ["_ga"]=> string(25) "GA1.2.97015029.1604338881" ["wpml_browser_redirect_test"]=> string(1) "0" ["wordpress_google_apps_login"]=> string(32) "437cf8211ec3deed5e2a99615d26dafa" ["_icl_visitor_lang_js"]=> string(5) "en-ca" ["_gid"]=> string(27) "GA1.2.1427479078.1624393391" ["wp-wpml_current_language"]=> string(2) "en" }