Simon Lacoste-Julien

aristidebaratin@hotmail.com

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

Reza Babanezhad Harikandeh

Independent visiting researcher - Samsung SAIT

babanezr@mila.quebec

Aristide Baratin

Independent visiting researcher - Samsung SAIT

PhD - Université de Montréal

vitoria.barin-pacela@mila.quebec

PhD - Université de Montréal

simon.dufort-labbe@mila.quebec

Marwa El Halabi

Independent visiting researcher - Samsung SAIT

marwa.el-halabi@mila.quebec

PhD - Université de Montréal

antonio-miguel.gois@mila.quebec

Yash Goyal

Independent visiting researcher - Samsung SAIT

yashgoyal.yg1@gmail.com

Meraj Hashemizadeh

Collaborating researcher - Université de Montréal

merajhse@mila.quebec

fahimeh.hosseini@mila.quebec

Fahimeh HosseiniNoohdani

Collaborating researcher - Université de Montréal

pedram.khorsandi@mila.quebec

Pedram Khorsandi

PhD - Université de Montréal

Boris Knyazev

Independent visiting researcher - Université de Montréal

Independent visiting researcher - Samsung - SAIT

lachaseb@mila.quebec

yukti.makhija@mila.quebec

Lucas Maes

PhD - Université de Montréal

lucas.maes@mila.quebec

PhD - Université de Montréal

Co-supervisor :

Ioannis Mitliagkas

PhD - Université de Montréal

Co-supervisor :

Aaron Courville

alan.milligan@mila.quebec

Collaborating Alumni - Université de Montréal

rozhin.nobahari@mila.quebec

Juan Ramirez

PhD - Université de Montréal

juan.ramirez@mila.quebec

PhD - Université de Montréal

mansi.rankawat@mila.quebec

Postdoctorate - Univeristy of Tübingen

Co-supervisor :

Theo Saulus

PhD - Université de Montréal

Co-supervisor :

Dhanya Sridhar

theo.saulus@mila.quebec

motahareh.sohrabi@mila.quebec

Damien Scieur

Independent visiting researcher - Samsung SAIT

Collaborating researcher - Université de Montréal

tianyue.zhang@mila.quebec

Tianyue (Helen) Zhang

PhD - Université de Montréal

Yan Zhang

Independent visiting researcher - Samsung SAIT

yan.zhang@mila.quebec

Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation

Blog Posts

March 18, 2024

Sébastien Lachapelle

Divyat Mahajan

Ioannis Mitliagkas

Simon Lacoste-Julien

Read the article

Publications

Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation

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

2023-12-11

Neural Information Processing Systems (Accept (oral))

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

Boris Knyazev

Doha Hwang

Pretraining a neural network on a large dataset is becoming a cornerstone in machine learning that is within the reach of only a few communi… (see more)ties with large-resources. We aim at an ambitious goal of democratizing pretraining. Towards that goal, we train and release a single neural network that can predict high quality ImageNet parameters of other neural networks. By using predicted parameters for initialization we are able to boost training of diverse ImageNet models available in PyTorch. When transferred to other datasets, models initialized with predicted parameters also converge faster and reach competitive final performance.

2023-07-24

ICML (Accept (Poster))

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… (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 labelled 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.

2023-07-24

International Conference on Machine Learning (Accept (Poster))

Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning

Although disentangled representations are often said to be beneficial for downstream tasks, current empirical and theoretical understanding … (see more)is limited. In this work, we provide evidence that disentangled representations coupled with sparse base-predictors improve generalization. In the context of multi-task learning, we prove a new identifiability result that provides conditions under which maximally sparse base-predictors yield disentangled representations. Motivated by this theoretical result, we propose a practical approach to learn disentangled representations based on a sparsity-promoting bi-level optimization problem. Finally, we explore a meta-learning version of this algorithm based on group Lasso multiclass SVM base-predictors, for which we derive a tractable dual formulation. It obtains competitive results on standard few-shot classification benchmarks, while each task is using only a fraction of the learned representations.

2023-07-24

International Conference on Machine Learning (Accept (Poster))

Unlocking Slot Attention by Changing Optimal Transport Costs

Yan Zhang

David W. Zhang

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.

2023-07-24

ICML (Accept (Poster))

A Survey of Self-Supervised and Few-Shot Object Detection

Gabriel Huang

Issam Hadj Laradji

David Vázquez

Pau Rodríguez

Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which require … (see more)dense labeling of the image. While few-shot object detection is about training a model on novel (unseen) object classes with little data, it still requires prior training on many labeled examples of base (seen) classes. On the other hand, self-supervised methods aim at learning representations from unlabeled data which transfer well to downstream tasks such as object detection. Combining few-shot and self-supervised object detection is a promising research direction. In this survey, we review and characterize the most recent approaches on few-shot and self-supervised object detection. Then, we give our main takeaways and discuss future research directions. Project page: https://gabrielhuang.github.io/fsod-survey/.

2023-03-31

IEEE Transactions on Pattern Analysis and Machine Intelligence (published)

arxiv.org

Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints

Jose Gallego-Posada

The performance of trained neural networks is robust to harsh levels of pruning. Coupled with the ever-growing size of deep learning models,… (see more) this observation has motivated extensive research on learning sparse models. In this work, we focus on the task of controlling the level of sparsity when performing sparse learning. Existing methods based on sparsity-inducing penalties involve expensive trial-and-error tuning of the penalty factor, thus lacking direct control of the resulting model sparsity. In response, we adopt a constrained formulation: using the gate mechanism proposed by Louizos et al. (2018), we formulate a constrained optimization problem where sparsification is guided by the training objective and the desired sparsity target in an end-to-end fashion. Experiments on CIFAR-{10, 100}, TinyImageNet, and ImageNet using WideResNet and ResNet{18, 50} models validate the effectiveness of our proposal and demonstrate that we can reliably achieve pre-determined sparsity targets without compromising on predictive performance.

2022-11-28

Conference on Neural Information Processing Systems (Accept)

Data-Efficient Structured Pruning via Submodular Optimization

Marwa El Halabi

Suraj Srinivas

Structured pruning is an effective approach for compressing large pre-trained neural networks without significantly affecting their performa… (see more)nce. However, most current structured pruning methods do not provide any performance guarantees, and often require fine-tuning, which makes them inapplicable in the limited-data regime. We propose a principled data-efficient structured pruning method based on submodular optimization. In particular, for a given layer, we select neurons/channels to prune and corresponding new weights for the next layer, that minimize the change in the next layer's input induced by pruning. We show that this selection problem is a weakly submodular maximization problem, thus it can be provably approximated using an efficient greedy algorithm. Our method is guaranteed to have an exponentially decreasing error between the original model and the pruned model outputs w.r.t the pruned size, under reasonable assumptions. It is also one of the few methods in the literature that uses only a limited-number of training data and no labels. Our experimental results demonstrate that our method outperforms state-of-the-art methods in the limited-data regime.

2022-11-28

Conference on Neural Information Processing Systems (Accept)

Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution

Antonio Orvieto

Nicolas Loizou

Recently, Loizou et al. (2021), proposed and analyzed stochastic gradient descent (SGD) with stochastic Polyak stepsize (SPS). The proposed … (see more)SPS comes with strong convergence guarantees and competitive performance; however, it has two main drawbacks when it is used in non-over-parameterized regimes: (i) It requires a priori knowledge of the optimal mini-batch losses, which are not available when the interpolation condition is not satisfied (e.g., regularized objectives), and (ii) it guarantees convergence only to a neighborhood of the solution. In this work, we study the dynamics and the convergence properties of SGD equipped with new variants of the stochastic Polyak stepsize and provide solutions to both drawbacks of the original SPS. We first show that a simple modification of the original SPS that uses lower bounds instead of the optimal function values can directly solve issue (i). On the other hand, solving issue (ii) turns out to be more challenging and leads us to valuable insights into the method's behavior. We show that if interpolation is not satisfied, the correlation between SPS and stochastic gradients introduces a bias, which effectively distorts the expectation of the gradient signal near minimizers, leading to non-convergence - even if the stepsize is scaled down during training. To fix this issue, we propose DecSPS, a novel modification of SPS, which guarantees convergence to the exact minimizer - without a priori knowledge of the problem parameters. For strongly-convex optimization problems, DecSPS is the first stochastic adaptive optimization method that converges to the exact solution without restrictive assumptions like bounded iterates/gradients.

2022-11-28

Conference on Neural Information Processing Systems (Accept)

Reza Babanezhad Harikandeh

SVRG meets AdaGrad: painless variance reduction

Benjamin Dubois-Taine

Sharan Vaswani

Mark Schmidt

2022-11-09

Machine Learning (published)

arxiv.org

Partial Disentanglement via Mechanism Sparsity

Sébastien Lachapelle

2022-07-08

auai.org/UAI/2022/Workshop/CRL (oral)

Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA

Sébastien Lachapelle

Pau Rodríguez

Yash Sharma

Katie E Everett

Rémi Le Priol

Alexandre Lacoste

This work introduces a novel principle we call disentanglement via mechanism sparsity regularization, which can be applied when the latent f… (see more)actors of interest depend sparsely on past latent factors and/or observed auxiliary variables. We propose a representation learning method that induces disentanglement by simultaneously learning the latent factors and the sparse causal graphical model that relates them. We develop a rigorous identifiability theory, building on recent nonlinear independent component analysis (ICA) results, that formalizes this principle and shows how the latent variables can be recovered up to permutation if one regularizes the latent mechanisms to be sparse and if some graph connectivity criterion is satisfied by the data generating process. As a special case of our framework, we show how one can leverage unknown-target interventions on the latent factors to disentangle them, thereby drawing further connections between ICA and causality. We propose a VAE-based method in which the latent mechanisms are learned and regularized via binary masks, and validate our theory by showing it learns disentangled representations in simulations.

2022-06-27

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