Simon Lacoste-Julien

research

∙ 07/18/2023

Promoting Exploration in Memory-Augmented Adam using Critical Momenta

Adaptive gradient-based optimizers, particularly Adam, have left their m...

0 Pranshu Malviya, et al. ∙

research

∙ 07/05/2023

Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation

We tackle the problems of latent variables identification and "out-of-su...

0 Sébastien Lachapelle, et al. ∙

research

∙ 06/28/2023

Identifiability of Discretized Latent Coordinate Systems via Density Landmarks Detection

Disentanglement aims to recover meaningful latent ground-truth factors f...

0 Vitória Barin Pacela, et al. ∙

research

∙ 04/06/2023

PopulAtion Parameter Averaging (PAPA)

Ensemble methods combine the predictions of multiple models to improve p...

0 Alexia Jolicoeur-Martineau, et al. ∙

research

∙ 03/07/2023

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

Pretraining a neural network on a large dataset is becoming a cornerston...

0 Boris Knyazev, et al. ∙

research

∙ 01/30/2023

Unlocking Slot Attention by Changing Optimal Transport Costs

Slot attention is a powerful method for object-centric modeling in image...

0 Yan Zhang, et al. ∙

research

∙ 12/03/2022

CrossSplit: Mitigating Label Noise Memorization through Data Splitting

We approach the problem of improving robustness of deep learning algorit...

0 Jihye Kim, et al. ∙

research

∙ 11/26/2022

Synergies Between Disentanglement and Sparsity: a Multi-Task Learning Perspective

Although disentangled representations are often said to be beneficial fo...

0 Sébastien Lachapelle, et al. ∙

research

∙ 08/08/2022

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

The performance of trained neural networks is robust to harsh levels of ...

1 Jose Gallego-Posada, et al. ∙

research

∙ 07/15/2022

Partial Disentanglement via Mechanism Sparsity

Disentanglement via mechanism sparsity was introduced recently as a prin...

9 Sébastien Lachapelle, et al. ∙

research

∙ 03/09/2022

Data-Efficient Structured Pruning via Submodular Optimization

Structured pruning is an effective approach for compressing large pre-tr...

8 Marwa El Halabi, et al. ∙

research

∙ 02/28/2022

Bayesian Structure Learning with Generative Flow Networks

In Bayesian structure learning, we are interested in inferring a distrib...

7 Tristan Deleu, et al. ∙

research

∙ 11/23/2021

Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation

Most set prediction models in deep learning use set-equivariant operatio...

4 Yan Zhang, et al. ∙

research

∙ 11/12/2021

Convergence Rates for the MAP of an Exponential Family and Stochastic Mirror Descent – an Open Problem

We consider the problem of upper bounding the expected log-likelihood su...

0 Rémi Le Priol, et al. ∙

research

∙ 10/27/2021

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

Labeling data is often expensive and time-consuming, especially for task...

77 Gabriel Huang, et al. ∙

research

∙ 07/21/2021

Discovering Latent Causal Variables via Mechanism Sparsity: A New Principle for Nonlinear ICA

It can be argued that finding an interpretable low-dimensional represent...

23 Sébastien Lachapelle, et al. ∙

research

∙ 06/30/2021

Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity

Two of the most prominent algorithms for solving unconstrained smooth ga...

6 Nicolas Loizou, et al. ∙

research

∙ 05/25/2021

Structured Convolutional Kernel Networks for Airline Crew Scheduling

Motivated by the needs from an airline crew scheduling application, we i...

0 Yassine Yaakoubi, et al. ∙

research

∙ 03/16/2021

Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning

Model-agnostic meta-learning (MAML) is a popular method for few-shot lea...

15 Namyeong Kwon, et al. ∙

research

∙ 03/02/2021

Online Adversarial Attacks

Adversarial attacks expose important vulnerabilities of deep learning mo...

0 Andjela Mladenovic, et al. ∙

research

∙ 02/18/2021

SVRG Meets AdaGrad: Painless Variance Reduction

Variance reduction (VR) methods for finite-sum minimization typically re...

4 Benjamin Dubois-Taine, et al. ∙

research

∙ 11/23/2020

Geometry-Aware Universal Mirror-Prox

Mirror-prox (MP) is a well-known algorithm to solve variational inequali...

0 Reza Babanezhad, et al. ∙

research

∙ 11/23/2020

On the Convergence of Continuous Constrained Optimization for Structure Learning

Structure learning of directed acyclic graphs (DAGs) is a fundamental pr...

0 Ignavier Ng, et al. ∙

research

∙ 09/30/2020

Machine Learning in Airline Crew Pairing to Construct Initial Clusters for Dynamic Constraint Aggregation

The crew pairing problem (CPP) is generally modelled as a set partitioni...

13 Yassine Yaakoubi, et al. ∙

research

∙ 09/26/2020

Flight-connection Prediction for Airline Crew Scheduling to Construct Initial Clusters for OR Optimizer

We present a case study of using machine learning classification algorit...

17 Yassine Yaakoubi, et al. ∙

research

∙ 08/03/2020

Implicit Regularization in Deep Learning: A View from Function Space

We approach the problem of implicit regularization in deep learning from...

39 Aristide Baratin, et al. ∙

research

∙ 07/08/2020

Stochastic Hamiltonian Gradient Methods for Smooth Games

The success of adversarial formulations in machine learning has brought ...

45 Nicolas Loizou, et al. ∙

research

∙ 07/03/2020

Differentiable Causal Discovery from Interventional Data

Discovering causal relationships in data is a challenging task that invo...

6 Philippe Brouillard, et al. ∙

research

∙ 07/01/2020

Adversarial Example Games

The existence of adversarial examples capable of fooling trained neural ...

13 Avishek Joey Bose, et al. ∙

research

∙ 06/11/2020

Adaptive Gradient Methods Converge Faster with Over-Parameterization (and you can do a line-search)

As adaptive gradient methods are typically used for training over-parame...

12 Sharan Vaswani, et al. ∙

research

∙ 05/18/2020

An Analysis of the Adaptation Speed of Causal Models

We consider the problem of discovering the causal process that generated...

6 Rémi Le Priol, et al. ∙

research

∙ 02/24/2020

Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence

We propose a stochastic variant of the classical Polyak step-size (Polya...

13 Nicolas Loizou, et al. ∙

research

∙ 01/02/2020

Accelerating Smooth Games by Manipulating Spectral Shapes

We use matrix iteration theory to characterize acceleration in smooth ga...

16 Waïss Azizian, et al. ∙

research

∙ 10/11/2019

Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation

We consider stochastic second order methods for minimizing strongly-conv...

11 Si Yi Meng, et al. ∙

research

∙ 06/19/2019

GEAR: Geometry-Aware Rényi Information

Shannon's seminal theory of information has been of paramount importance...

3 Jose Gallego, et al. ∙

research

∙ 06/13/2019

A Tight and Unified Analysis of Extragradient for a Whole Spectrum of Differentiable Games

We consider differentiable games: multi-objective minimization problems,...

0 Waïss Azizian, et al. ∙

research

∙ 06/11/2019

A Closer Look at the Optimization Landscapes of Generative Adversarial Networks

Generative adversarial networks have been very successful in generative ...

1 Hugo Berard, et al. ∙

research

∙ 06/05/2019

Gradient-Based Neural DAG Learning

We propose a novel score-based approach to learning a directed acyclic g...

3 Sébastien Lachapelle, et al. ∙

research

∙ 05/24/2019

Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates

Recent works have shown that stochastic gradient descent (SGD) achieves ...

10 Sharan Vaswani, et al. ∙

research

∙ 04/30/2019

Implicit Regularization of Discrete Gradient Dynamics in Deep Linear Neural Networks

When optimizing over-parameterized models, such as deep neural networks,...

2 Gauthier Gidel, et al. ∙

research

∙ 04/18/2019

Reducing Noise in GAN Training with Variance Reduced Extragradient

Using large mini-batches when training generative adversarial networks (...

38 Tatjana Chavdarova, et al. ∙

research

∙ 02/22/2019

Centroid Networks for Few-Shot Clustering and Unsupervised Few-Shot Classification

Traditional clustering algorithms such as K-means rely heavily on the na...

1 Gabriel Huang, et al. ∙

research

∙ 01/22/2019

Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information

This paper offers a methodological contribution at the intersection of m...

14 Eric Larsen, et al. ∙

research

∙ 10/26/2018

Quantifying Learning Guarantees for Convex but Inconsistent Surrogates

We study consistency properties of machine learning methods based on min...

0 Kirill Struminsky, et al. ∙

research

∙ 10/19/2018

A Modern Take on the Bias-Variance Tradeoff in Neural Networks

We revisit the bias-variance tradeoff for neural networks in light of mo...

20 Brady Neal, et al. ∙

research

∙ 09/17/2018

Scattering Networks for Hybrid Representation Learning

Scattering networks are a class of designed Convolutional Neural Network...

5 Edouard Oyallon, et al. ∙

research

∙ 07/31/2018

Predicting Solution Summaries to Integer Linear Programs under Imperfect Information with Machine Learning

The paper provides a methodological contribution at the intersection of ...

2 Eric Larsen, et al. ∙

research

∙ 07/12/2018

Negative Momentum for Improved Game Dynamics

Games generalize the optimization paradigm by introducing different obje...

11 Gauthier Gidel, et al. ∙

research

∙ 04/09/2018

Frank-Wolfe Splitting via Augmented Lagrangian Method

Minimizing a function over an intersection of convex sets is an importan...

0 Gauthier Gidel, et al. ∙

research

∙ 02/28/2018

A Variational Inequality Perspective on Generative Adversarial Nets

Stability has been a recurrent issue in training generative adversarial ...

0 Gauthier Gidel, et al. ∙

Simon Lacoste-Julien

Featured Co-authors