Portrait of Hugo Larochelle

Hugo Larochelle

Core Industry Member
Canada CIFAR AI Chair
Adjunct professor, Université de Montréal, Depatment of Computer Science and Operations Research
Research Scientist, Google DeepMind
Research Topics
Deep Learning
Google Scholar
X

Biography

I am a researcher in the Google DeepMind (previously Google Brain) team in Montréal, an adjunct professor at Université de Montréal, and a Canada CIFAR AI Chair. My research focuses on the study and development of deep learning algorithms.

Current Students

Sangnie Bhardwaj
PhD - Université de Montréal
Principal supervisor :
Guillaume Lajoie
Mélisande Astrid Crystal Teng
PhD - Université de Montréal
Principal supervisor :
Yoshua Bengio
Website
Github
Hattie Zhou
PhD - Université de Montréal
Co-supervisor :
Aaron Courville

Publications

On Catastrophic Interference in Atari 2600 Games
William Fedus
Dibya Ghosh
John D. Martin
Marc Gendron-Bellemare
Yoshua Bengio
Hugo Larochelle
Model-free deep reinforcement learning is sample inefficient. One hypothesis -- speculated, but not confirmed -- is that catastrophic interf… (see more)erence within an environment inhibits learning. We test this hypothesis through a large-scale empirical study in the Arcade Learning Environment (ALE) and, indeed, find supporting evidence. We show that interference causes performance to plateau; the network cannot train on segments beyond the plateau without degrading the policy used to reach there. By synthetically controlling for interference, we demonstrate performance boosts across architectures, learning algorithms and environments. A more refined analysis shows that learning one segment of a game often increases prediction errors elsewhere. Our study provides a clear empirical link between catastrophic interference and sample efficiency in reinforcement learning.
2020-02-28
ArXiv (preprint)
arxiv.org
arxiv.org
Language GANs Falling Short
Massimo Caccia
Lucas Caccia
William Fedus
Hugo Larochelle
Joelle Pineau
Laurent Charlin
Generating high-quality text with sufficient diversity is essential for a wide range of Natural Language Generation (NLG) tasks. Maximum-Lik… (see more)elihood (MLE) models trained with teacher forcing have consistently been reported as weak baselines, where poor performance is attributed to exposure bias (Bengio et al., 2015; Ranzato et al., 2015); at inference time, the model is fed its own prediction instead of a ground-truth token, which can lead to accumulating errors and poor samples. This line of reasoning has led to an outbreak of adversarial based approaches for NLG, on the account that GANs do not suffer from exposure bias. In this work, we make several surprising observations which contradict common beliefs. First, we revisit the canonical evaluation framework for NLG, and point out fundamental flaws with quality-only evaluation: we show that one can outperform such metrics using a simple, well-known temperature parameter to artificially reduce the entropy of the model's conditional distributions. Second, we leverage the control over the quality / diversity trade-off given by this parameter to evaluate models over the whole quality-diversity spectrum and find MLE models constantly outperform the proposed GAN variants over the whole quality-diversity space. Our results have several implications: 1) The impact of exposure bias on sample quality is less severe than previously thought, 2) temperature tuning provides a better quality / diversity trade-off than adversarial training while being easier to train, easier to cross-validate, and less computationally expensive. Code to reproduce the experiments is available at github.com/pclucas14/GansFallingShort
2020-01-01
ICLR (published)
openreview.net
openreview.net
Learning Graph Structure With A Finite-State Automaton Layer
Daniel D. Johnson
Hugo Larochelle
Daniel Tarlow
arxiv.org
Small-GAN: Speeding Up GAN Training Using Core-sets
Samarth Sinha
Han Zhang
Anirudh Goyal
Yoshua Bengio
Hugo Larochelle
Augustus Odena
Recent work by Brock et al. (2018) suggests that Generative Adversarial Networks (GANs) benefit disproportionately from large mini-batch siz… (see more)es. Unfortunately, using large batches is slow and expensive on conventional hardware. Thus, it would be nice if we could generate batches that were effectively large though actually small. In this work, we propose a method to do this, inspired by the use of Coreset-selection in active learning. When training a GAN, we draw a large batch of samples from the prior and then compress that batch using Coreset-selection. To create effectively large batches of 'real' images, we create a cached dataset of Inception activations of each training image, randomly project them down to a smaller dimension, and then use Coreset-selection on those projected activations at training time. We conduct experiments showing that this technique substantially reduces training time and memory usage for modern GAN variants, that it reduces the fraction of dropped modes in a synthetic dataset, and that it allows GANs to reach a new state of the art in anomaly detection.
2020-01-01
ICML (published)
proceedings.mlr.press
openreview.net
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
Yoshua Bengio
We show that the sum of the implicit generator log-density …
arxiv.org
InfoBot: Transfer and Exploration via the Information Bottleneck
Anirudh Goyal
Riashat Islam
DJ Strouse
Zafarali Ahmed
Matthew Botvinick
Hugo Larochelle
Sergey Levine
Yoshua Bengio
A central challenge in reinforcement learning is discovering effective policies for tasks where rewards are sparsely distributed. We postula… (see more)te that in the absence of useful reward signals, an effective exploration strategy should seek out {\it decision states}. These states lie at critical junctions in the state space from where the agent can transition to new, potentially unexplored regions. We propose to learn about decision states from prior experience. By training a goal-conditioned policy with an information bottleneck, we can identify decision states by examining where the model actually leverages the goal state. We find that this simple mechanism effectively identifies decision states, even in partially observed settings. In effect, the model learns the sensory cues that correlate with potential subgoals. In new environments, this model can then identify novel subgoals for further exploration, guiding the agent through a sequence of potential decision states and through new regions of the state space.
2019-01-01
ICLR.cc/2019/Conference (poster)
openreview.net
openreview.net