167 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Université de MontréalCA31 papers
- McGill UniversityCA16 papers
- Mila - Quebec Artificial Intelligence InstituteCA11 papers
- Concordia UniversityCA5 papers
- Flatiron Health (United States)US5 papers
- Flatiron Institute5 papers
- Google DeepMind (United Kingdom)GB5 papers
- Meta (Israel)IL5 papers
- Canadian Institute for Advanced ResearchCA4 papers
- Polytechnique MontréalCA4 papers
- University of TorontoCA4 papers
- Google (United States)US3 papers
30 papers · 1 filter
ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training
Adel Nabli, Louis Fournier, Pierre Erbacher +3
Training LLMs relies on distributed implementations using multiple GPUs to compute gradients in parallel with sharded optimizers. However, synchronizing gradients in data parallel…
PETRA: Parallel End-to-end Training with Reversible Architectures
Stéphane Rivaud, Louis Fournier, Thomas Pumir +3
Reversible architectures have been shown to be capable of performing on par with their non-reversible architectures, being applied in deep learning for memory savings and generativ…
WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Average
Louis Fournier, Adel Nabli, Masih Aminbeidokhti +3
The performance of deep neural networks is enhanced by ensemble methods, which average the output of several models. However, this comes at an increased cost at inference. Weight a…
Can Forward Gradient Match Backpropagation?
Louis Fournier, Stéphane Rivaud, Eugene Belilovsky +2
Forward Gradients - the idea of using directional derivatives in forward differentiation mode - have recently been shown to be utilizable for neural network training while avoiding…
: Accelerating Asynchronous Communication in Decentralized Deep Learning
Adel Nabli, Eugene Belilovsky, Edouard Oyallon
Distributed training of Deep Learning models has been critical to many recent successes in the field. Current standard methods primarily rely on synchronous centralized algorithms…
Knowledge Distillation for Federated Learning: a Practical Guide
Alessio Mora, Irene Tenison, Paolo Bellavista +1
Federated Learning (FL) enables the training of Deep Learning models without centrally collecting possibly sensitive raw data. The most used algorithms for FL are parameter-averagi…
A Highly Adaptive Acoustic Model for Accurate Multi-Dialect Speech Recognition
Sanghyun Yoo, Inchul Song, Yoshua Bengio
Despite the success of deep learning in speech recognition, multi-dialect speech recognition remains a difficult problem. Although dialect-specific acoustic models are known to per…
Equivariant Networks for Pixelized Spheres
Mehran Shakerinava, Siamak Ravanbakhsh
Pixelizations of Platonic solids such as the cube and icosahedron have been widely used to represent spherical data, from climate records to Cosmic Microwave Background maps. Plato…
Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous Distributed Learning
Eugene Belilovsky, Louis Leconte, Lucas Caccia +2
A commonly cited inefficiency of neural network training using back-propagation is the update locking problem: each layer must wait for the signal to propagate through the full net…
Randomized Exploration for Reinforcement Learning with General Value Function Approximation
Haque Ishfaq, Qiwen Cui, Viet Nguyen +5
We propose a model-free reinforcement learning algorithm inspired by the popular randomized least squares value iteration (RLSVI) algorithm as well as the optimism principle. Unlik…
Structured Convolutional Kernel Networks for Airline Crew Scheduling
Yassine Yaakoubi, François Soumis, Simon Lacoste-Julien
Motivated by the needs from an airline crew scheduling application, we introduce structured convolutional kernel networks (Struct-CKN), which combine CKNs from Mairal et al. (2014)…
Continuous Coordination As a Realistic Scenario for Lifelong Learning
Hadi Nekoei, Akilesh Badrinaaraayanan, Aaron Courville +1
Current deep reinforcement learning (RL) algorithms are still highly task-specific and lack the ability to generalize to new environments. Lifelong learning (LLL), however, aims at…
Variance Penalized On-Policy and Off-Policy Actor-Critic
Arushi Jain, Gandharv Patil, Ayush Jain +2
Reinforcement learning algorithms are typically geared towards optimizing the expected return of an agent. However, in many practical applications, low variance in the return is de…
Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards
Susan Amin, Maziar Gomrokchi, Hossein Aboutalebi +2
A major challenge in reinforcement learning is the design of exploration strategies, especially for environments with sparse reward structures and continuous state and action space…
Regularized Inverse Reinforcement Learning
Wonseok Jeon, Chen-Yang Su, Paul Barde +3
Inverse Reinforcement Learning (IRL) aims to facilitate a learner's ability to imitate expert behavior by acquiring reward functions that explain the expert's decisions. Regularize…
Directional Graph Networks
Dominique Beaini, Saro Passaro, Vincent Létourneau +3
The lack of anisotropic kernels in graph neural networks (GNNs) strongly limits their expressiveness, contributing to well-known issues such as over-smoothing. To overcome this lim…
Beyond variance reduction: Understanding the true impact of baselines on policy optimization
Wesley Chung, Valentin Thomas, Marlos C. Machado +1
Bandit and reinforcement learning (RL) problems can often be framed as optimization problems where the goal is to maximize average performance while having access only to stochasti…
Revisiting Fundamentals of Experience Replay
William Fedus, Prajit Ramachandran, Rishabh Agarwal +4
Experience replay is central to off-policy algorithms in deep reinforcement learning (RL), but there remain significant gaps in our understanding. We therefore present a systematic…
Stochastic Hamiltonian Gradient Methods for Smooth Games
Nicolas Loizou, Hugo Berard, Alexia Jolicoeur-Martineau +3
The success of adversarial formulations in machine learning has brought renewed motivation for smooth games. In this work, we focus on the class of stochastic Hamiltonian methods a…
What can I do here? A Theory of Affordances in Reinforcement Learning
Khimya Khetarpal, Zafarali Ahmed, Gheorghe Comanici +2
Reinforcement learning algorithms usually assume that all actions are always available to an agent. However, both people and animals understand the general link between the feature…
Revisiting Loss Modelling for Unstructured Pruning
César Laurent, Camille Ballas, Thomas George +2
By removing parameters from deep neural networks, unstructured pruning methods aim at cutting down memory footprint and computational cost, while maintaining prediction accuracy. I…
Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation
Xiang Jiang, Qicheng Lao, Stan Matwin +1
We present an approach for unsupervised domain adaptation---with a strong focus on practical considerations of within-domain class imbalance and between-domain class distribution s…
Inductive Relation Prediction by Subgraph Reasoning
Komal K. Teru, Etienne Denis, William L. Hamilton
The dominant paradigm for relation prediction in knowledge graphs involves learning and operating on latent representations (i.e., embeddings) of entities and relations. However, t…
On the Learning Dynamics of Deep Neural Networks
Remi Tachet, Mohammad Pezeshki, Samira Shabanian +2
While a lot of progress has been made in recent years, the dynamics of learning in deep nonlinear neural networks remain to this day largely misunderstood. In this work, we study t…