Guillaume Lajoie

matteo.alleman@mila.quebec

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

Matteo Alleman

Postdoctorate - Université de Montréal

Rohan Banerjee

Collaborating Alumni - Polytechnique Montréal

rohan.banerjee@mila.quebec

Independent visiting researcher - N/A

philippe.beaudoin@mila.quebec

PhD - Université de Montréal

Co-supervisor :

Hugo Larochelle

sangnie.bhardwaj@mila.quebec

Colin Bredenberg

Independent visiting researcher - Université de Montréal

Co-supervisor :

colin.bredenberg@mila.quebec

Leo Choiniere

PhD - Université de Montréal

leo.choiniere@mila.quebec

Claudia Clopath

Independent visiting researcher - University College London

claudia.clopath@mila.quebec

Eric Elmoznino

PhD - Université de Montréal

Principal supervisor :

Yoshua Bengio

eric.elmoznino@mila.quebec

Leo Gagnon

PhD - Université de Montréal

leo.gagnon@mila.quebec

Tom George

Postdoctorate - McGill University

Principal supervisor :

tomgeorge1@btinternet.com

Juan Guerra

PhD - Polytechnique Montréal

juan.guerra@mila.quebec

thomas.jiralerspong@mila.quebec

Nanda Harishankar Krishna

PhD - Université de Montréal

Anna Jahn

Independent visiting researcher - McGill University

anna.jahn1@mila.quebec

Chen Jiang

PhD - McGill University

Principal supervisor :

Paul Masset

chen.jiang@mila.quebec

Thomas Jiralerspong

PhD - Université de Montréal

Co-supervisor :

Yoshua Bengio

Master's Research - Université de Montréal

Co-supervisor :

Dhanya Sridhar

tejaskasetty@gmail.com

PhD - McGill University

Principal supervisor :

pingsheng.li@mila.quebec

mathys.loiselle@mila.quebec

Mathys Loiselle

Research Intern - Concordia University

Co-supervisor :

Matt Perich

Ximeng Mao

PhD - Université de Montréal

Co-supervisor :

Joelle Pineau

ximeng.mao@mila.quebec

Abdel Mfougouon Njupoun

PhD - Université de Montréal

Co-supervisor :

alexandre.payeur@mila.quebec

abdelnjupoun@gmail.com

PhD - Université de Montréal

Co-supervisor :

Independent visiting researcher - Université de Montréal

Julia Price

Master's Research - Université de Montréal

julia.price@mila.quebec

Mauricio Rivera

Master's Research - Université de Montréal

Principal supervisor :

Marco Bonizzato

mauriv2010@gmail.com

hee-woon.ryoo@mila.quebec

Avery Ryoo

PhD - Université de Montréal

Principal supervisor :

Matt Perich

PhD - Université de Montréal

Co-supervisor :

Lune Bellec

sainathp@mila.quebec

ezekiel.williams@mila.quebec

Ryan Vogt

Postdoctorate - Université de Montréal

ryan.vogt@mila.quebec

Ezekiel Williams

PhD - Université de Montréal

Independent visiting researcher - University of Western Ontario

jinkang.xiang@mila.quebec

Blog Posts

Représentation graphique d'un nerf vague

May 21, 2025

Machine Learning for the Segmentation of Different Nerve Fibre Activations from Brain-to-body Neural Signals

Param Raval

Olivier Tessier-Larivière

Pascal Fortier-Poisson

Blake Richards

Guillaume Lajoie

Read the article

June 13, 2024

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

Roman Pogodin

Jonathan Cornford

Arna Ghosh

Gauthier Gidel

Guillaume Lajoie

Blake Richards

Read the article

Publications

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.

2024-07-16

ArXiv (preprint)

arxiv.org

Expressivity of Neural Networks with Fixed Weights and Learned Biases

Ezekiel Williams

Avery Hee-Woon Ryoo

Thomas Jiralerspong

Alexandre Payeur

Matthew G Perich

Luca Mazzucato

2024-06-15

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

Olivier Tessier-Larivière

Using neural biomarkers to personalize dosing of vagus nerve stimulation

Antonin Berthon

Lorenz Wernisch

Myrta Stoukidi

Michael Thornton

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

Vagus nerve stimulation (VNS) is an established therapy for treating a variety of chronic diseases, such as epilepsy, depression, obesity, a… (see more)nd for stroke rehabilitation. However, lack of precision and side-effects have hindered its efficacy and extension to new conditions. To achieve a better understanding of the relationship between VNS parameters and neural and physiological responses to enable the design of personalized dosing procedures to improve precision and efficacy of VNS therapies. We used biomarkers from recorded evoked neural activity and short-term physiological responses (throat muscle, cardiac and respiratory activity) to understand the response to a wide range of VNS parameters in anaesthetised pigs. Using signal processing, Gaussian processes (GP) and parametric regression models we analyse the relationship between VNS parameters and neural and physiological responses. Firstly, we observe inter-subject variability for both neural and physiological responses. Secondly, we illustrate how considering multiple stimulation parameters in VNS dosing can improve the efficacy and precision of VNS therapies. Thirdly, we describe the relationship between different VNS parameters and the evoked neural activity and show how spatially selective electrodes can be used to improve fibre recruitment. Fourthly, we provide a detailed exploration of the relationship between the activations of neural fibre types and different physiological effects, and show that recordings of evoked neural activity are powerful biomarkers for predicting the short-term physiological effects of VNS. Finally, based on these results, we discuss how recordings of evoked neural activity can help design VNS dosing procedures that optimize short-term physiological effects safely and efficiently. Understanding of evoked neural activity during VNS provide powerful biomarkers that could improve the precision, safety and efficacy of VNS therapies.

2024-06-15

Bioelectronic Medicine (published)

Amortizing Intractable Inference in Large Language Models

Edward J. Hu

Nikolay Malkin

Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This l… (see more)imits tractable querying of this knowledge to start-to-end autoregressive sampling. However, many tasks of interest -- including sequence continuation, infilling, and other forms of constrained generation -- involve sampling from intractable posterior distributions. We address this limitation by using amortized Bayesian inference to sample from these intractable posteriors. Such amortization is algorithmically achieved by fine-tuning LLMs via diversity-seeking reinforcement learning algorithms: generative flow networks (GFlowNets). We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training and reward-maximizing policy optimization. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem and demonstrate that our approach enables data-efficient adaptation of LLMs to tasks that require multi-step rationalization and tool use.

2024-05-06

International Conference on Learning Representations (Accept (oral))

Delta-AI: Local Objectives for Amortized Inference in Sparse Graphical Models

Jean-Pierre Falet

Hae Beom Lee

Nikolay Malkin

Chen Sun

We present a new algorithm for amortized inference in sparse probabilistic graphical models (PGMs), which we call …

2024-05-06

International Conference on Learning Representations (Accept (poster))

How Connectivity Structure Shapes Rich and Lazy Learning in Neural Circuits

Yuhan Helena Liu

Aristide Baratin

Jonathan Cornford

Stefan Mihalas

Eric Shea-Brown

In theoretical neuroscience, recent work leverages deep learning tools to explore how some network attributes critically influence its learn… (see more)ing dynamics. Notably, initial weight distributions with small (resp. large) variance may yield a rich (resp. lazy) regime, where significant (resp. minor) changes to network states and representation are observed over the course of learning. However, in biology, neural circuit connectivity could exhibit a low-rank structure and therefore differs markedly from the random initializations generally used for these studies. As such, here we investigate how the structure of the initial weights -- in particular their effective rank -- influences the network learning regime. Through both empirical and theoretical analyses, we discover that high-rank initializations typically yield smaller network changes indicative of lazier learning, a finding we also confirm with experimentally-driven initial connectivity in recurrent neural networks. Conversely, low-rank initialization biases learning towards richer learning. Importantly, however, as an exception to this rule, we find lazier learning can still occur with a low-rank initialization that aligns with task and data statistics. Our research highlights the pivotal role of initial weight structures in shaping learning regimes, with implications for metabolic costs of plasticity and risks of catastrophic forgetting.

2024-05-06

International Conference on Learning Representations (Accept (poster))

LEAD: Min-Max Optimization from a Physical Perspective

Reyhane Askari Hemmat

Amartya Mitra

Ioannis Mitliagkas

Adversarial formulations have rekindled interest in two-player min-max games. A central obstacle in the optimization of such games is the ro… (see more)tational dynamics that hinder their convergence. In this paper, we show that game optimization shares dynamic properties with particle systems subject to multiple forces, and one can leverage tools from physics to improve optimization dynamics. Inspired by the physical framework, we propose LEAD, an optimizer for min-max games. Next, using Lyapunov stability theory from dynamical systems as well as spectral analysis, we study LEAD’s convergence properties in continuous and discrete time settings for a class of quadratic min-max games to demonstrate linear convergence to the Nash equilibrium. Finally, we empirically evaluate our method on synthetic setups and CIFAR-10 image generation to demonstrate improvements in GAN training.

2024-05-06

International Conference on Learning Representations (Accept (Poster))

Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency

Tianhong Li

Sangnie Bhardwaj

Yonglong Tian

Han Zhang

Jarred Barber

Dina Katabi

Huiwen Chang

Dilip Krishnan

Current vision-language generative models rely on expansive corpora of paired image-text data to attain optimal performance and generalizati… (see more)on capabilities. However, automatically collecting such data (e.g. via large-scale web scraping) leads to low quality and poor image-text correlation, while human annotation is more accurate but requires significant manual effort and expense. We introduce

2024-05-06

International Conference on Learning Representations (Accept (spotlight))

Synaptic Weight Distributions Depend on the Geometry of Plasticity

Blake Aaron Richards

A growing literature in computational neuroscience leverages gradient descent and learning algorithms that approximate it to study synaptic … (see more)plasticity in the brain. However, the vast majority of this work ignores a critical underlying assumption: the choice of distance for synaptic changes - i.e. the geometry of synaptic plasticity. Gradient descent assumes that the distance is Euclidean, but many other distances are possible, and there is no reason that biology necessarily uses Euclidean geometry. Here, using the theoretical tools provided by mirror descent, we show that the distribution of synaptic weights will depend on the geometry of synaptic plasticity. We use these results to show that experimentally-observed log-normal weight distributions found in several brain areas are not consistent with standard gradient descent (i.e. a Euclidean geometry), but rather with non-Euclidean distances. Finally, we show that it should be possible to experimentally test for different synaptic geometries by comparing synaptic weight distributions before and after learning. Overall, our work shows that the current paradigm in theoretical work on synaptic plasticity that assumes Euclidean synaptic geometry may be misguided and that it should be possible to experimentally determine the true geometry of synaptic plasticity in the brain.

2024-05-06

International Conference on Learning Representations (Accept (spotlight))

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. Over time, task-relevant information became concentrated in fewer neurons, unlike with fixed decoders. At the population level, task information also became largely confined to a few neural modes that accounted for an unexpectedly small fraction of the population variance. A neural network model suggests the adaptive decoders directly contribute to forming these more 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.

2024-03-19

bioRxiv (preprint)

Olivier Tessier-Larivière

Online Bayesian optimization of vagus nerve stimulation

Lorenz Wernisch

Tristan Edwards

Antonin Berthon

Elvijs Sarkans

Myrta Stoukidi

Pascal Fortier-Poisson

Max Pinkney

Michael Thornton

Catherine Hanley

Susannah Lee

Joel Jennings

Ben Appleton

Phillip Garsed

Bret Patterson

Will Buttinger

Samuel Gonshaw

Matjaž Jakopec

Sudhakaran Shunmugam

Jorin Mamen … (see 4 more)

Aleksi Tukiainen

Oliver Armitage

Emil Hewage

Objective. In bioelectronic medicine, neuromodulation therapies induce neural signals to the brain or organs, modifying their function. Stim… (see more)ulation devices capable of triggering exogenous neural signals using electrical waveforms require a complex and multi-dimensional parameter space to control such waveforms. Determining the best combination of parameters (waveform optimization or dosing) for treating a particular patient’s illness is therefore challenging. Comprehensive parameter searching for an optimal stimulation effect is often infeasible in a clinical setting due to the size of the parameter space. Restricting this space, however, may lead to suboptimal therapeutic results, reduced responder rates, and adverse effects. Approach. As an alternative to a full parameter search, we present a flexible machine learning, data acquisition, and processing framework for optimizing neural stimulation parameters, requiring as few steps as possible using Bayesian optimization. This optimization builds a model of the neural and physiological responses to stimulations, enabling it to optimize stimulation parameters and provide estimates of the accuracy of the response model. The vagus nerve (VN) innervates, among other thoracic and visceral organs, the heart, thus controlling heart rate (HR), making it an ideal candidate for demonstrating the effectiveness of our approach. Main results. The efficacy of our optimization approach was first evaluated on simulated neural responses, then applied to VN stimulation intraoperatively in porcine subjects. Optimization converged quickly on parameters achieving target HRs and optimizing neural B-fiber activations despite high intersubject variability. Significance. An optimized stimulation waveform was achieved in real time with far fewer stimulations than required by alternative optimization strategies, thus minimizing exposure to side effects. Uncertainty estimates helped avoiding stimulations outside a safe range. Our approach shows that a complex set of neural stimulation parameters can be optimized in real-time for a patient to achieve a personalized precision dosing.

2024-03-12

Journal of Neural Engineering (published)