Guillaume Lajoie

Biography

Guillaume Lajoie is an Associate professor in the Department of Mathematics and Statistics at Université de Montréal and a Core Academic Member of Mila – Quebec Artificial Intelligence Institute. He holds a Canada-CIFAR AI Research Chair, and a Canada Research Chair (CRC) in Neural Computation and Interfacing.

His research is positioned at the intersection of AI and Neuroscience where he develops tools to better understand mechanisms of intelligence common to both biological and artificial systems. His research group's contributions range from advances in multi-scale learning paradigms for large artificial systems, to applications in neurotechnology. Dr. Lajoie is actively involved in responsible AI development efforts, seeking to identify guidelines and best practices for use of AI in research and beyond.

Current Students

Federico Arangath Joseph

Collaborating researcher - ETH Zurich

Stefan Bauer

Independent visiting researcher

Principal supervisor :

Yoshua Bengio

Sangnie Bhardwaj

PhD - Université de Montréal

Co-supervisor :

Hugo Larochelle

Colin Bredenberg

Postdoctorate - Université de Montréal

Co-supervisor :

Leo Choiniere

PhD - Université de Montréal

Olivier Codol

Postdoctorate - Université de Montréal

Co-supervisor :

Matt Perich

Eric Elmoznino

PhD - Université de Montréal

Principal supervisor :

PhD - Université de Montréal

Principal supervisor :

Leo Gagnon

PhD - Université de Montréal

Juan Guerra

Master's Research - Polytechnique Montréal

Principal supervisor :

Marco Bonizzato

Website

Nanda Harishankar Krishna

PhD - Université de Montréal

Collaborating researcher - Western Washington University (faculty; assistant prof))

Principal supervisor :

Master's Research - Université de Montréal

Co-supervisor :

Collaborating researcher - Université de Montréal

Ximeng Mao

PhD - Université de Montréal

Co-supervisor :

Joelle Pineau

Abdel Mfougouon Njupoun

PhD - Université de Montréal

Co-supervisor :

PhD - Université de Montréal

Co-supervisor :

Amine Natik

PhD - Université de Montréal

Co-supervisor :

Guy Wolf

François Paugam

PhD - Université de Montréal

Principal supervisor :

Lune Bellec

Alexandre Payeur

Collaborating researcher - Université de Montréal

Mohammad Pezeshki

Collaborating researcher

Principal supervisor :

Postdoctorate - McGill University

Principal supervisor :

Param Raval

Collaborating Alumni - Université de Montréal

Avery Ryoo

Master's Research - Université de Montréal

Principal supervisor :

PhD - Université de Montréal

Co-supervisor :

Lune Bellec

Laura Suarez

PhD - McGill University

Ryan Vogt

Postdoctorate - Université de Montréal

Vivian White

Research Intern - Western Washington University

Co-supervisor :

PhD - Université de Montréal

Website

What Do Synaptic Weight Distributions Tell Us About Learning in the Brain ?

Blog Posts

June 13, 2024

Roman Pogodin

Jonathan Cornford

Arna Ghosh

Gauthier Gidel

Guillaume Lajoie

Blake Richards

Read the article

Publications

Brain-like learning with exponentiated gradients

Jonathan Cornford

Roman Pogodin

Arna Ghosh

Kaiwen Sheng

Brendan A. Bicknell

Olivier Codol

Beverley A. Clark

2024-10-26

bioRxiv (preprint)

Multi-agent cooperation through learning-aware policy gradients

Alexander Meulemans

Seijin Kobayashi

Johannes von Oswald

Nino Scherrer

Eric Elmoznino

Blaise Agüera y Arcas

João Sacramento

Self-interested individuals often fail to cooperate, posing a fundamental challenge for multi-agent learning. How can we achieve cooperation… (see more) among self-interested, independent learning agents? Promising recent work has shown that in certain tasks cooperation can be established between learning-aware agents who model the learning dynamics of each other. Here, we present the first unbiased, higher-derivative-free policy gradient algorithm for learning-aware reinforcement learning, which takes into account that other agents are themselves learning through trial and error based on multiple noisy trials. We then leverage efficient sequence models to condition behavior on long observation histories that contain traces of the learning dynamics of other agents. Training long-context policies with our algorithm leads to cooperative behavior and high returns on standard social dilemmas, including a challenging environment where temporally-extended action coordination is required. Finally, we derive from the iterated prisoner's dilemma a novel explanation for how and when cooperation arises among self-interested learning-aware agents.

2024-10-24

ArXiv (preprint)

A Complexity-Based Theory of Compositionality

Eric Elmoznino

Thomas Jiralerspong

Yoshua Bengio

2024-10-18

ArXiv (preprint)

Learning Stochastic Rainbow Networks

Vivian White

Muawiz Sajjad Chaudhary

Guy Wolf

Kameron Decker Harris

Random feature models are a popular approach for studying network learning that can capture important behaviors while remaining simpler than… (see more) traditional training. Guth et al. [2024] introduced “rainbow” networks which model the distribution of trained weights as correlated random features conditioned on previous layer activity. Sampling new weights from distributions fit to learned networks led to similar performance in entirely untrained networks, and the observed weight covariance were found to be low rank. This provided evidence that random feature models could be extended to some networks away from initialization, but White et al. [2024] failed to replicate their results in the deeper ResNet18 architecture. Here we ask whether the rainbow formulation can succeed in deeper networks by directly training a stochastic ensemble of random features, which we call stochastic rainbow networks. At every gradient descent iteration, new weights are sampled for all intermediate layers and features aligned layer-wise. We find: (1) this approach scales to deeper models, which outperform shallow networks at large widths; (2) ensembling multiple samples from the stochastic model is better than retraining the classifier head; and (3) low-rank parameterization of the learnable weight covariances can approach the accuracy of full-rank networks. This offers more evidence for rainbow and other structured random feature networks as reduced models of deep learning.

2024-10-10

NeurIPS.cc/2024/Workshop/SciForDL (poster)

openreview.net

The oneirogen hypothesis: modeling the hallucinatory effects of classical psychedelics in terms of replay-dependent plasticity mechanisms

Colin Bredenberg

Fabrice Normandin

2024-09-30

bioRxiv (preprint)

Accelerating Training with Neuron Interaction and Nowcasting Networks

Boris Knyazev

Abhinav Moudgil

Eugene Belilovsky

Simon Lacoste-Julien

Neural network training can be accelerated when a learnable update rule is used in lieu of classic adaptive optimizers (e.g. Adam). However,… (see more) learnable update rules can be costly and unstable to train and use. A simpler recently proposed approach to accelerate training is to use Adam for most of the optimization steps and periodically, only every few steps, nowcast (predict future) parameters. We improve this approach by Neuron interaction and Nowcasting (NiNo) networks. NiNo leverages neuron connectivity and graph neural networks to more accurately nowcast parameters by learning in a supervised way from a set of training trajectories over multiple tasks. We show that in some networks, such as Transformers, neuron connectivity is non-trivial. By accurately modeling neuron connectivity, we allow NiNo to accelerate Adam training by up to 50\% in vision and language tasks.

2024-09-06

ArXiv (preprint)

When can transformers compositionally generalize in-context?

Seijin Kobayashi

Simon Schug

Yassir Akram

Florian Redhardt

Johannes von Oswald

Razvan Pascanu

João Sacramento

Many tasks can be composed from a few independent components. This gives rise to a combinatorial explosion of possible tasks, only some of w… (see more)hich might be encountered during training. Under what circumstances can transformers compositionally generalize from a subset of tasks to all possible combinations of tasks that share similar components? Here we study a modular multitask setting that allows us to precisely control compositional structure in the data generation process. We present evidence that transformers learning in-context struggle to generalize compositionally on this task despite being in principle expressive enough to do so. Compositional generalization becomes possible only when introducing a bottleneck that enforces an explicit separation between task inference and task execution.

2024-07-17

ArXiv (preprint)

Expressivity of Neural Networks with Random Weights and Learned Biases

Ezekiel Williams

Avery Hee-Woon Ryoo

Thomas Jiralerspong

Alexandre Payeur

Matt Perich

Luca Mazzucato

2024-07-01

ArXiv (preprint)

Using neural biomarkers to personalize dosing of vagus nerve stimulation

Antonin Berthon

Lorenz Wernisch

Myrta Stoukidi

Michael Thornton

Olivier Tessier-Lariviere

Pascal Fortier-Poisson

Jorin Mamen

Max Pinkney

Susannah Lee

Elvijs Sarkans

Luca Annecchino

Ben Appleton

Philip Garsed

Bret Patterson

Samuel Gonshaw

Matjaž Jakopec

Sudhakaran Shunmugam

Tristan Edwards

Aleksi Tukiainen

Joel Jennings … (see 3 more)

Emil Hewage

Oliver Armitage

2024-06-17

Bioelectronic Medicine (published)

Expressivity of Neural Networks with Fixed Weights and Learned Biases

Ezekiel Williams

Avery Hee-Woon Ryoo

Thomas Jiralerspong

Alexandre Payeur

Matt Perich

Luca Mazzucato

2024-06-16

ICML.cc/2024/Workshop/HiLD (poster)

openreview.net

Does learning the right latent variables necessarily improve in-context learning?

Sarthak Mittal

Eric Elmoznino

L'eo Gagnon

Sangnie Bhardwaj

Dhanya Sridhar

Large autoregressive models like Transformers can solve tasks through in-context learning (ICL) without learning new weights, suggesting ave… (see more)nues for efficiently solving new tasks. For many tasks, e.g., linear regression, the data factorizes: examples are independent given a task latent that generates the data, e.g., linear coefficients. While an optimal predictor leverages this factorization by inferring task latents, it is unclear if Transformers implicitly do so or if they instead exploit heuristics and statistical shortcuts enabled by attention layers. Both scenarios have inspired active ongoing work. In this paper, we systematically investigate the effect of explicitly inferring task latents. We minimally modify the Transformer architecture with a bottleneck designed to prevent shortcuts in favor of more structured solutions, and then compare performance against standard Transformers across various ICL tasks. Contrary to intuition and some recent works, we find little discernible difference between the two; biasing towards task-relevant latent variables does not lead to better out-of-distribution performance, in general. Curiously, we find that while the bottleneck effectively learns to extract latent task variables from context, downstream processing struggles to utilize them for robust prediction. Our study highlights the intrinsic limitations of Transformers in achieving structured ICL solutions that generalize, and shows that while inferring the right latents aids interpretability, it is not sufficient to alleviate this problem.

2024-05-29

ArXiv (preprint)

Assistive sensory-motor perturbations influence learned neural representations

Pavithra Rajeswaran

Alexandre Payeur

Amy L. Orsborn

Task errors are used to learn and refine motor skills. We investigated how task assistance influences learned neural representations using B… (see more)rain-Computer Interfaces (BCIs), which map neural activity into movement via a decoder. We analyzed motor cortex activity as monkeys practiced BCI with a decoder that adapted to improve or maintain performance over days. Population dimensionality remained constant or increased with learning, counter to trends with non-adaptive BCIs. Yet, over time, task information was contained in a smaller subset of neurons or population modes. Moreover, task information was ultimately stored in neural modes that occupied a small fraction of the population variance. An artificial neural network model suggests the adaptive decoders contribute to forming these compact neural representations. Our findings show that assistive decoders manipulate error information used for long-term learning computations, like credit assignment, which informs our understanding of motor learning and has implications for designing real-world BCIs.

2024-03-20

bioRxiv (preprint)