papers

Publications (20)

cs.LG2023

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

Sébastien Lachapelle, Tristan Deleu, Divyat Mahajan +4

Although disentangled representations are often said to be beneficial for downstream tasks, current empirical and theoretical understanding is limited. In this work, we provide evi…

cs.LG2025

On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity

Quentin Bertrand, Anne Gagneux, Mathurin Massias +1

Modern deep generative models can now produce high-quality synthetic samples that are often indistinguishable from real training data. A growing body of research aims to understand…

stat.ML2020

Handling correlated and repeated measurements with the smoothed multivariate square-root Lasso

Quentin Bertrand, Mathurin Massias, Alexandre Gramfort +1

Sparsity promoting norms are frequently used in high dimensional regression. A limitation of such Lasso-type estimators is that the optimal regularization parameter depends on the…

stat.ML2021

Anderson acceleration of coordinate descent

Quentin Bertrand, Mathurin Massias

Acceleration of first order methods is mainly obtained via inertial techniques à la Nesterov, or via nonlinear extrapolation. The latter has known a recent surge of interest, with…

cs.AI2017

Anytime Exact Belief Propagation

Gabriel Azevedo Ferreira, Quentin Bertrand, Charles Maussion +1

Statistical Relational Models and, more recently, Probabilistic Programming, have been making strides towards an integration of logic and probabilistic reasoning. A natural expecta…

cs.GT2023

On the Limitations of Elo: Real-World Games, are Transitive, not Additive

Quentin Bertrand, Wojciech Marian Czarnecki, Gauthier Gidel

Real-world competitive games, such as chess, go, or StarCraft II, rely on Elo models to measure the strength of their players. Since these games are not fully transitive, using Elo…

math.PR2018

Dimension improvement in Dhar's refutation of the Eden conjecture

Quentin Bertrand, Jules Pertinand

We consider the Eden model on the d-dimensional hypercubical unoriented lattice , for large d. Initially, every lattice point is healthy, except the origin which is infected. Then,…

physics.app-ph2024

Multipacting mitigation by atomic layer deposition: the case study of Titanium Nitride

Yasmine Kalboussi, Sarah Dadouch, Baptiste Delatte +15

This study investigates the use of Atomic Layer deposition (ALD) to mitigate multipacting phenomena inside superconducting radio frequency (SRF) cavities used in particle accelerat…

stat.ML2023

Beyond L1: Faster and Better Sparse Models with skglm

Quentin Bertrand, Quentin Klopfenstein, Pierre-Antoine Bannier +2

We propose a new fast algorithm to estimate any sparse generalized linear model with convex or non-convex separable penalties. Our algorithm is able to solve problems with millions…

physics.acc-ph2023

The Control System of the Elliptical Cavity and Cryomodule Test Stand Demonstrator for ESS

Alexis Gaget, Tom Joannem, Adelino Gomes +3

CEA IRFU Saclay is taking part of ESS (European Spallation Source) construction through several packages and, especially in the last three years on the Elliptical Cavity and Cryomo…

stat.ML2020

Implicit differentiation of Lasso-type models for hyperparameter optimization

Quentin Bertrand, Quentin Klopfenstein, Mathieu Blondel +3

Setting regularization parameters for Lasso-type estimators is notoriously difficult, though crucial in practice. The most popular hyperparameter optimization approach is grid-sear…

cs.CV2024

Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences

Damien Ferbach, Quentin Bertrand, Avishek Joey Bose +1

The rapid progress in generative models has resulted in impressive leaps in generation quality, blurring the lines between synthetic and real data. Web-scale datasets are now prone…

math.OC2023

The Curse of Unrolling: Rate of Differentiating Through Optimization

Damien Scieur, Quentin Bertrand, Gauthier Gidel +1

Computing the Jacobian of the solution of an optimization problem is a central problem in machine learning, with applications in hyperparameter optimization, meta-learning, optimiz…

cs.LG2024

On the Stability of Iterative Retraining of Generative Models on their own Data

Quentin Bertrand, Avishek Joey Bose, Alexandre Duplessis +2

Deep generative models have made tremendous progress in modeling complex data, often exhibiting generation quality that surpasses a typical human's ability to discern the authentic…

cs.LG2024

Omega: Optimistic EMA Gradients

Juan Ramirez, Rohan Sukumaran, Quentin Bertrand +1

Stochastic min-max optimization has gained interest in the machine learning community with the advancements in GANs and adversarial training. Although game optimization is fairly w…

eess.IV2021

Electromagnetic neural source imaging under sparsity constraints with SURE-based hyperparameter tuning

Pierre-Antoine Bannier, Quentin Bertrand, Joseph Salmon +1

Estimators based on non-convex sparsity-promoting penalties were shown to yield state-of-the-art solutions to the magneto-/electroencephalography (M/EEG) brain source localization…

stat.ML2020

Model identification and local linear convergence of coordinate descent

Quentin Klopfenstein, Quentin Bertrand, Alexandre Gramfort +2

For composite nonsmooth optimization problems, Forward-Backward algorithm achieves model identification (e.g. support identification for the Lasso) after a finite number of iterati…

cs.GT2025

Self-Play Q-learners Can Provably Collude in the Iterated Prisoner's Dilemma

Quentin Bertrand, Juan Duque, Emilio Calvano +1

A growing body of computational studies shows that simple machine learning agents converge to cooperative behaviors in social dilemmas, such as collusive price-setting in oligopoly…

stat.ML2022

Implicit differentiation for fast hyperparameter selection in non-smooth convex learning

Quentin Bertrand, Quentin Klopfenstein, Mathurin Massias +4

Finding the optimal hyperparameters of a model can be cast as a bilevel optimization problem, typically solved using zero-order techniques. In this work we study first-order method…

stat.ML2020

Support recovery and sup-norm convergence rates for sparse pivotal estimation

Mathurin Massias, Quentin Bertrand, Alexandre Gramfort +1

In high dimensional sparse regression, pivotal estimators are estimators for which the optimal regularization parameter is independent of the noise level. The canonical pivotal est…