Simon Lacoste-Julien

Core Academic Member

Canada CIFAR AI Chair

Associate Scientific Director, Mila, Associate Professor, Université de Montréal, Department of Computer Science and Operations Research

Vice President and Lab Director, Samsung Advanced Institute of Technology (SAIT) AI Lab, Montréal

Website

Google Scholar

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

Alexia Jolicoeur-Martineau

Independent visiting researcher - Samsung SAIT

PhD - Université de Montréal

antonio-miguel.gois@mila.quebec

Independent visiting researcher - Samsung SAIT

Independent visiting researcher - Université de Montréal

Independent visiting researcher - Samsung SAIT

PhD - McGill University

Principal supervisor :

Adam M. Oberman

george.orfanides@mila.quebec

Jaewoo Lee

Independent visiting researcher - Pohang University of Science and Technology in Pohang, Korea

jaewoo.lee@mila.quebec

Jose Gallego Posada

PhD - Université de Montréal

PhD - Université de Montréal

juan.ramirez@mila.quebec

Website

Github

Google Scholar

Kiho Cho

Independent visiting researcher - Samsung SAIT

kiho.cho@mila.quebec

Kwon Kisoo

Independent visiting researcher - Seoul National University, Korea

kwon.kisoo@mila.quebec

Lucas Maes

PhD - Université de Montréal

lucas.maes@mila.quebec

Website

Github

Mansi Rankawat

PhD - Université de Montréal

mansi.rankawat@mila.quebec

Independent visiting researcher - Samsung SAIT

marwa.el-halabi@mila.quebec

Collaborating researcher - Université de Montréal

merajhse@mila.quebec

Github

Michelle Liu

Collaborating researcher

liumiche@mila.quebec

Motahareh Sohrabi

Master's Research - Université de Montréal

motahareh.sohrabi@mila.quebec

Website

Pedram Khorsandi

PhD - Université de Montréal

pedram.khorsandi@mila.quebec

Github

Google Scholar

Quentin Bertrand

Postdoctorate - Université de Montréal

Principal supervisor :

Gauthier Gidel

quentin.bertrand@mila.quebec

Website

Github

Google Scholar

Reza Babanezhad Harikandeh

Independent visiting researcher - Samsung SAIT

babanezr@mila.quebec

Rozhin Nobahari

Master's Research - Université de Montréal

rozhin.nobahari@mila.quebec

Sébastien Lachapelle

PhD - Université de Montréal

lachaseb@mila.quebec

Website

Google Scholar

Helen Zhang

PhD - Université de Montréal

tianyue.zhang@mila.quebec

Website

Github

Vitoria Barin Pacela

PhD - Université de Montréal

vitoria.barin-pacela@mila.quebec

Website

Github

Google Scholar

Yan Zhang

Independent visiting researcher - Samsung SAIT

yan.zhang@mila.quebec

Website

Github

Google Scholar

Yash Goyal

Independent visiting researcher - Samsung SAIT

yash.goyal@mila.quebec

Website

Blog Posts

March 18, 2024

Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation

Sébastien Lachapelle

Divyat Mahajan

Ioannis Mitliagkas

Simon Lacoste-Julien

Read the article

Publications

Promoting Exploration in Memory-Augmented Adam using Critical Momenta

Pranshu Malviya

Goncalo Mordido

Aristide Baratin

Reza Babanezhad Harikandeh

Jerry Huang

Simon Lacoste-Julien

Razvan Pascanu

Sarath Chandar Anbil Parthipan

Adaptive gradient-based optimizers, particularly Adam, have left their mark in training large-scale deep learning models. The strength of su… (see more)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.

2024-06-09

TMLR (accepted)

doi.org

openreview.net

Weight-Sharing Regularization

Mehran Shakerinava

Motahareh Sohrabi

Siamak Ravanbakhsh

Simon Lacoste-Julien

2024-04-18

Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (published)

doi.org

arxiv.org

PopulAtion Parameter Averaging (PAPA)

Alexia Jolicoeur-Martineau

Emy Gervais

Kilian FATRAS

Yan Zhang

Simon Lacoste-Julien

2024-04-05

TMLR (accepted)

doi.org

openreview.net

On the Identifiability of Quantized Factors

Vitória Barin Pacela

Kartik Ahuja

Simon Lacoste-Julien

Pascal Vincent

Disentanglement aims to recover meaningful latent ground-truth factors from the observed distribution solely, and is formalized through the… (see more) 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.

2024-03-15

Proceedings of the Third Conference on Causal Learning and Reasoning (published)

proceedings.mlr.press

arxiv.org

Balancing Act: Constraining Disparate Impact in Sparse Models

Meraj Hashemizadeh

Juan Ramirez

Rohan Sukumaran

Golnoosh Farnadi

Simon Lacoste-Julien

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 … (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.

2024-01-16

ICLR.cc/2024/Conference (poster)

doi.org

openreview.net

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

Simon Lacoste-Julien

2024-01-10

ArXiv (preprint)

doi.org

arxiv.org

Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation

Sébastien Lachapelle

Divyat Mahajan

Ioannis Mitliagkas

Simon Lacoste-Julien

We tackle the problems of latent variables identification and "out-of-support'' image generation in representation learning. We show that bo… (see more)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.

openreview.net

Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?

Boris Knyazev

DOHA HWANG

Simon Lacoste-Julien

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (published)

doi.org

openreview.net

CrossSplit: Mitigating Label Noise Memorization through Data Splitting

Jihye Kim

Aristide Baratin

Yan Zhang

Simon Lacoste-Julien

We approach the problem of improving robustness of deep learning algorithms in the presence of label noise. Building upon existing label cor… (see more)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/.

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (published)

doi.org

openreview.net

Unlocking Slot Attention by Changing Optimal Transport Costs

Yan Zhang

David W Zhang

Simon Lacoste-Julien

Gertjan J. Burghouts

Cees G. M. Snoek

Slot attention is a powerful method for object-centric modeling in images and videos. However, its set-equivariance limits its ability to ha… (see more)ndle videos with a dynamic number of objects because it cannot break ties. To overcome this limitation, we first establish a connection between slot attention and optimal transport. Based on this new perspective we propose **MESH** (Minimize Entropy of Sinkhorn): a cross-attention module that combines the tiebreaking properties of unregularized optimal transport with the speed of regularized optimal transport. We evaluate slot attention using MESH on multiple object-centric learning benchmarks and find significant improvements over slot attention in every setting.

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (published)

doi.org

openreview.net

On the Identifiability of Quantized Factors

Vitória Barin Pacela

Kartik Ahuja

Simon Lacoste-Julien

Pascal Vincent

Disentanglement aims to recover meaningful latent ground-truth factors from the observed distribution solely, and is formalized through the … (see more)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.

2023-06-28

ArXiv (preprint)

arxiv.org

Identifiability of Discretized Latent Coordinate Systems via Density Landmarks Detection

Vitória Barin-Pacela

Kartik Ahuja

Simon Lacoste-Julien

Pascal Vincent

Disentanglement aims to recover meaningful latent ground-truth factors from only the observed distribution. Identifiability provides the the… (see more)oretical grounding for disentanglement to be well-founded. Unfortunately, unsupervised identifiability of independent latent factors is a theoretically proven impossibility in the i.i.d. setting under a general nonlinear smooth map from factors to observations. In this work, we show that, remarkably, it is possible to recover discretized latent coordinates under a highly generic nonlinear smooth mapping (a diffeomorphism) without any additional inductive bias on the mapping. This is, assuming that latent density has axis-aligned discontinuity landmarks, but without making the unrealistic assumption of statistical independence of the factors. We introduce this novel form of identifiability, termed quantized coordinate identifiability , and provide a comprehensive proof of the recovery of discretized coordinates.

2023-06-19

ICML.cc/2023/Workshop/SPIGM (poster)

doi.org

openreview.net

AI Research Driven by Real-World Problems

AI Policy Compass

Student Life and Resources

Simon Lacoste-Julien

Biography

Current Students

Blog Posts

Publications

AI Research Driven by Real-World Problems

AI Policy Compass

Student Life and Resources

Popular keywords:

Simon Lacoste-Julien

Biography

Current Students

Blog Posts

Publications