Portrait de Simon Lacoste-Julien

Simon Lacoste-Julien

Membre académique principal
Chaire en IA Canada-CIFAR
Directeur scientifique adjoint, Mila, Professeur agrégé, Université de Montréal, Département d'informatique et de recherche opérationnelle
Vice-président et directeur de laboratoire, Samsung Advanced Institute of Technology (SAIT) AI Lab, Montréal
Sujets de recherche
Apprentissage profond
Causalité
Modèles génératifs
Modèles probabilistes
Optimisation
Théorie de l'apprentissage automatique
Traitement du langage naturel
Vision par ordinateur

Biographie

Simon Lacoste-Julien est professeur agrégé au Département d'informatique et de recherche opérationnelle (DIRO) de l'Université de Montréal, membre cofondateur de Mila – Institut québécois d’intelligence artificielle et titulaire d'une chaire en IA Canada-CIFAR. Il dirige également à temps partiel le SAIT AI Lab Montréal.

Ses recherches portent sur l'apprentissage automatique et les mathématiques appliquées, et intègrent des applications à la vision artificielle et au traitement du langage naturel. Il a obtenu une licence en mathématiques, physique et informatique à l’Université McGill, un doctorat en informatique à l’Université de Californie à Berkeley et un postdoctorat à l'Université de Cambridge.

Il a passé quelques années à l'Institut national de recherche en sciences et technologies du numérique (INRIA) et à l'École normale supérieure de Paris en tant que professeur de recherche avant de revenir à Montréal, en 2016, pour répondre à l'appel de Yoshua Bengio et contribuer à la croissance de l'écosystème de l'IA à Montréal.

Étudiants actuels

Visiteur de recherche indépendant - Samsung SAIT
Visiteur de recherche indépendant - Samsung SAIT
Postdoctorat - UdeM
Superviseur⋅e principal⋅e :
Visiteur de recherche indépendant - Samsung SAIT
Visiteur de recherche indépendant - Samsung SAIT
Collaborateur·rice alumni - UdeM
Visiteur de recherche indépendant - Samsung SAIT
Collaborateur·rice de recherche - UdeM
Visiteur de recherche indépendant - Samsung SAIT
Visiteur de recherche indépendant - Seoul National University, Korea
Visiteur de recherche indépendant - UdeM
Visiteur de recherche indépendant - Pohang University of Science and Technology in Pohang, Korea
Collaborateur·rice de recherche
Doctorat - UdeM
Maîtrise recherche - UdeM
Visiteur de recherche indépendant - Samsung SAIT
Collaborateur·rice de recherche - UdeM
Doctorat - UdeM
Visiteur de recherche indépendant - Samsung SAIT

Publications

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,… (voir plus) 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.
On PI Controllers for Updating Lagrange Multipliers in Constrained Optimization
Motahareh Sohrabi
Juan Ramirez
Tianyue H. Zhang
Jose Gallego-Posada
Constrained optimization offers a powerful framework to prescribe desired behaviors in neural network models. Typically, constrained problem… (voir plus)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 νPI algorithm and contributes an optimization perspective on Lagrange multiplier updates based on PI controllers, extending the work of Stooke, Achiam and Abbeel (2020). We provide theoretical and empirical insights explaining the inability of momentum methods to address the shortcomings of gradient descent-ascent, and contrast this with the empirical success of our proposed νPI controller. Moreover, we prove that νPI generalizes popular momentum methods for single-objective minimization. Our experiments demonstrate that νPI reliably stabilizes the multiplier dynamics and its hyperparameters enjoy robust and predictable behavior.
Performative Prediction on Games and Mechanism Design
António Góis
Mehrnaz Mofakhami
Fernando P. Santos
Promoting Exploration in Memory-Augmented Adam using Critical Momenta
Pranshu Malviya
Goncalo Mordido
Aristide Baratin
Reza Babanezhad Harikandeh
Jerry Huang
Razvan Pascanu
Adaptive gradient-based optimizers, particularly Adam, have left their mark in training large-scale deep learning models. The strength of su… (voir plus)ch optimizers is that they exhibit fast convergence while being more robust to hyperparameter choice. However, they often generalize worse than non-adaptive methods. Recent studies have tied this performance gap to flat minima selection: adaptive methods tend to find solutions in sharper basins of the loss landscape, which in turn hurts generalization. To overcome this issue, we propose a new memory-augmented version of Adam that promotes exploration towards flatter minima by using a buffer of critical momentum terms during training. Intuitively, the use of the buffer makes the optimizer overshoot outside the basin of attraction if it is not wide enough. We empirically show that our method improves the performance of several variants of Adam on standard supervised language modelling and image classification tasks.
Weight-Sharing Regularization
Mehran Shakerinava
Motahareh Sohrabi
PopulAtion Parameter Averaging (PAPA)
Alexia Jolicoeur-Martineau
Emy Gervais
Kilian FATRAS
Yan Zhang
On the Identifiability of Quantized Factors
Vitória Barin Pacela
Kartik Ahuja
Disentanglement aims to recover meaningful latent ground-truth factors from the observed distribution solely, and is formalized through the… (voir plus) theory of identifiability. The identifiability of independent latent factors is proven to be impossible in the unsupervised i.i.d. setting under a general nonlinear map from factors to observations. In this work, however, we demonstrate that it is possible to recover quantized latent factors under a generic nonlinear diffeomorphism. We only assume that the latent factors have independent discontinuities in their density, without requiring the factors to be statistically independent. We introduce this novel form of identifiability, termed quantized factor identifiability, and provide a comprehensive proof of the recovery of the quantized factors.
Balancing Act: Constraining Disparate Impact in Sparse Models
Meraj Hashemizadeh
Juan Ramirez
Rohan Sukumaran
Jose Gallego-Posada
Model pruning is a popular approach to enable the deployment of large deep learning models on edge devices with restricted computational or … (voir plus)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.
Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies
Sébastien Lachapelle
Pau Rodriguez
Yash Sharma
Katie Everett
Rémi LE PRIOL
Alexandre Lacoste
Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation
Sébastien Lachapelle
Divyat Mahajan
We tackle the problems of latent variables identification and "out-of-support'' image generation in representation learning. We show that bo… (voir plus)th are possible for a class of decoders that we call additive, which are reminiscent of decoders used for object-centric representation learning (OCRL) and well suited for images that can be decomposed as a sum of object-specific images. We provide conditions under which exactly solving the reconstruction problem using an additive decoder is guaranteed to identify the blocks of latent variables up to permutation and block-wise invertible transformations. This guarantee relies only on very weak assumptions about the distribution of the latent factors, which might present statistical dependencies and have an almost arbitrarily shaped support. Our result provides a new setting where nonlinear independent component analysis (ICA) is possible and adds to our theoretical understanding of OCRL methods. We also show theoretically that additive decoders can generate novel images by recombining observed factors of variations in novel ways, an ability we refer to as Cartesian-product extrapolation. We show empirically that additivity is crucial for both identifiability and extrapolation on simulated data.
Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?
Boris Knyazev
DOHA HWANG
CrossSplit: Mitigating Label Noise Memorization through Data Splitting
Jihye Kim
Aristide Baratin
Yan Zhang
We approach the problem of improving robustness of deep learning algorithms in the presence of label noise. Building upon existing label cor… (voir plus)rection and co-teaching methods, we propose a novel training procedure to mitigate the memorization of noisy labels, called CrossSplit, which uses a pair of neural networks trained on two disjoint parts of the labeled dataset. CrossSplit combines two main ingredients: (i) Cross-split label correction. The idea is that, since the model trained on one part of the data cannot memorize example-label pairs from the other part, the training labels presented to each network can be smoothly adjusted by using the predictions of its peer network; (ii) Cross-split semi-supervised training. A network trained on one part of the data also uses the unlabeled inputs of the other part. Extensive experiments on CIFAR-10, CIFAR-100, Tiny-ImageNet and mini-WebVision datasets demonstrate that our method can outperform the current state-of-the-art in a wide range of noise ratios. The project page is at https://rlawlgul.github.io/.