Portrait of Simon Lacoste-Julien

Simon Lacoste-Julien

Core Academic Member
Canada CIFAR AI Chair
Associate Scientific Director, Mila, Full Professor, Université de Montréal
Vice President and Lab Director, Samsung Advanced Institute of Technology (SAIT) AI Lab, Montréal
Research Topics
Causality
Computer Vision
Deep Learning
Generative Models
Machine Learning Theory
Natural Language Processing
Optimization
Probabilistic Models

Biography

Simon Lacoste-Julien is an associate professor at Mila – Quebec Artificial Intelligence Institute and in the Department of Computer Science and Operations Research (DIRO) at Université de Montréal. He is also a Canada CIFAR AI Chair and heads (part time) the SAIT AI Lab Montréal.

Lacoste-Julien‘s research interests are machine learning and applied mathematics, along with their applications to computer vision and natural language processing. He completed a BSc in mathematics, physics and computer science at McGill University, a PhD in computer science at UC Berkeley and a postdoc at the University of Cambridge.

After spending several years as a researcher at INRIA and the École normale supérieure in Paris, he returned to his home city of Montréal in 2016 to answer Yoshua Bengio’s call to help grow the Montréal AI ecosystem.

Current Students

PhD - Université de Montréal
Co-supervisor :
Independent visiting researcher - Samsung SAIT
Independent visiting researcher - Samsung SAIT
PhD - Université de Montréal
Independent visiting researcher - Samsung SAIT
Independent visiting researcher - Samsung SAIT
Collaborating researcher - Université de Montréal
Collaborating researcher - Université de Montréal
Independent visiting researcher - Samsung - SAIT
Postdoctorate - Univeristy of Tübingen
Co-supervisor :
PhD - Université de Montréal
Co-supervisor :
Independent visiting researcher - Samsung SAIT
Collaborating researcher - Université de Montréal
Independent visiting researcher - Samsung SAIT

Publications

Understanding Adam Requires Better Rotation Dependent Assumptions
Despite its widespread adoption, Adam's advantage over Stochastic Gradient Descent (SGD) lacks a comprehensive theoretical explanation. This… (see more) paper investigates Adam's sensitivity to rotations of the parameter space. We observe that Adam's performance in training transformers degrades under random rotations of the parameter space, indicating a crucial sensitivity to the choice of basis in practice. This reveals that conventional rotation-invariant assumptions are insufficient to capture Adam's advantages theoretically. To better understand the rotation-dependent properties that benefit Adam, we also identify structured rotations that preserve or even enhance its empirical performance. We then examine the rotation-dependent assumptions in the literature and find that they fall short in explaining Adam's behaviour across various rotation types. In contrast, we verify the orthogonality of the update as a promising indicator of Adam's basis sensitivity, suggesting it may be the key quantity for developing rotation-dependent theoretical frameworks that better explain its empirical success.
Operationalizing Quantized Disentanglement
Vitória Barin-Pacela
P Vincent
Quantized Disentanglement: A Practical Approach
Vitória Barin-Pacela
P Vincent
Position: Adopt Constraints Over Fixed Penalties in Deep Learning
Recent efforts to develop trustworthy AI systems have increased interest in learning problems with explicit requirements, or constraints. In… (see more) deep learning, however, such problems are often handled through fixed weighted-sum penalization: the constraints are added to the task loss with fixed coefficients, and the resulting scalarized objective is minimized. This position paper argues that fixed penalization is often ill-suited for deep learning problems with non-negotiable requirements for several reasons. First, in non-convex settings, the penalized and constrained problems are generally not equivalent, so solving the former need not solve the latter. Second, fixed penalization weakens hard requirements into soft penalties to be traded off against task performance. Third, choosing penalty coefficients to indirectly solve the constrained problem often involves costly trial and error, because changing them alters the penalized objective itself, and hence can mean solving the wrong problem altogether. We therefore argue that, when a deep learning problem specifies non-negotiable requirements, the constrained formulation itself should be the starting point, not the surrogate problem defined by fixed penalization. The appropriate solution strategy should then be chosen based on the problem's structure and scale.
Accelerating Training with Neuron Interaction and Nowcasting Networks
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. Recently, Jang et al. (2023) proposed a simpler approach to accelerate training based on weight nowcaster networks (WNNs). In their approach, Adam is used for most of the optimization steps and periodically, only every few steps, a WNN nowcasts (predicts near future) parameters. We improve WNNs by proposing neuron interaction and nowcasting (NiNo) networks. In contrast to WNNs, NiNo leverages neuron connectivity and graph neural networks to more accurately nowcast parameters. We further show that in some networks, such as Transformers, modeling neuron connectivity accurately is challenging. We address this and other limitations, which allows NiNo to accelerate Adam training by up to 50% in vision and language tasks.
Feasible Learning
Ignacio Hounie
Juan Elenter
Jose Gallego-Posada
Alejandro Ribeiro
We introduce Feasible Learning (FL), a sample-centric learning paradigm where models are trained by solving a feasibility problem that bound… (see more)s the loss for each training sample. In contrast to the ubiquitous Empirical Risk Minimization (ERM) framework, which optimizes for average performance, FL demands satisfactory performance \emph{on every individual data point}. Since any model that meets the prescribed performance threshold is a valid FL solution, the choice of optimization algorithm and its dynamics play a crucial role in shaping the properties of the resulting solutions. In particular, we study a primal-dual approach which dynamically re-weights the importance of each sample during training. To address the challenge of setting a meaningful threshold in practice, we introduce a relaxation of FL that incorporates slack variables of minimal norm. Our empirical analysis, spanning image classification, age regression, and preference optimization in large language models, demonstrates that models trained via FL can learn from data while displaying improved tail behavior compared to ERM, with only a marginal impact on average performance.
Performative Prediction on Games and Mechanism Design
On PI Controllers for Updating Lagrange Multipliers in Constrained Optimization
Tianyue H. Zhang
Jose Gallego-Posada
Constrained optimization offers a powerful framework to prescribe desired behaviors in neural network models. Typically, constrained problem… (see more)s are solved via their min-max Lagrangian formulations, which exhibit unstable oscillatory dynamics when optimized using gradient descent-ascent. The adoption of constrained optimization techniques in the machine learning community is currently limited by the lack of reliable, general-purpose update schemes for the Lagrange multipliers. This paper proposes the
Promoting Exploration in Memory-Augmented Adam using Critical Momenta
Adaptive gradient-based optimizers, notably Adam, have left their mark in training large-scale deep learning models, offering fast convergen… (see more)ce and robustness to hyperparameter settings. However, they often struggle with generalization, attributed to their tendency to converge to sharp minima in the loss landscape. To address this, we propose a new memory-augmented version of Adam that encourages exploration towards flatter minima by incorporating a buffer of critical momentum terms during training. This buffer prompts the optimizer to overshoot beyond narrow minima, promoting exploration. Through comprehensive analysis in simple settings, we illustrate the efficacy of our approach in increasing exploration and bias towards flatter minima. We empirically demonstrate that it can improve model performance for image classification on ImageNet and CIFAR10/100, language modelling on Penn Treebank, and online learning tasks on TinyImageNet and 5-dataset. Our code is available at https://github.com/chandar-lab/CMOptimizer.
Balancing Act: Constraining Disparate Impact in Sparse Models
Model pruning is a popular approach to enable the deployment of large deep learning models on edge devices with restricted computational or … (see more)storage capacities. Although sparse models achieve performance comparable to that of their dense counterparts at the level of the entire dataset, they exhibit high accuracy drops for some data sub-groups. Existing methods to mitigate this disparate impact induced by pruning (i) rely on surrogate metrics that address the problem indirectly and have limited interpretability; or (ii) scale poorly with the number of protected sub-groups in terms of computational cost. We propose a constrained optimization approach that directly addresses the disparate impact of pruning: our formulation bounds the accuracy change between the dense and sparse models, for each sub-group. This choice of constraints provides an interpretable success criterion to determine if a pruned model achieves acceptable disparity levels. Experimental results demonstrate that our technique scales reliably to problems involving large models and hundreds of protected sub-groups.
Weight-Sharing Regularization
Weight-sharing is ubiquitous in deep learning. Motivated by this, we propose a "weight-sharing regularization" penalty on the weights …
PopulAtion Parameter Averaging (PAPA)