Papers

• 2025

  • Q. Bertrand, A. Gagneux, M. Massias, R. Emonet On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity

  • Q. Bertrand, J. Duque, E. Calvano, G. Gidel Q-learners Can Provably Collude in the Iterated Prisoner's Dilemma, ICML 2025

  • M. Massias, B. Moufad, Q. Bertrand skglm: Improving scikit-learn for regularized Generalized Linear Models, ICML 2025 CODEML Workshop

  • A. Gagneux, S. Martin, R. Emonet, Q. Bertrand, M. Massias A Visual Dive into Conditional Flow Matching, ICLR 2025, Blog Post Track

• 2024

  • D. Ferbach, Q. Bertrand, A. J. Bose, G. Gidel Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences, NeurIPS 2024 (with spotlight!), slides

  • Q. Bertrand, A. J. Bose, A. Duplessis, M. Jiralerspong, G. Gidel On the Stability of Iterative Retraining of Generative Models on their own Data, ICLR 2024 (with spotlight!), code, slides, video

• 2023

  • J. Ramirez, R. Sukumaran, Q. Bertrand, G. Gidel, Omega: Optimistic EMA Gradients, ICML 2023 LatinX in AI Workshop, code

  • S. Lachapelle, T. Deleu, D. Mahajan, I. Mitliagkas, Y. Bengio, S. Lacoste-Julien, Q. Bertrand, Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning, ICML 2023

  • Q. Bertrand, W. M. Czarnecki, G. Gidel On the Limitations of Elo: Real-World Games are Transitive, not Additive, AISTATS 2023

  • Q. Klopfenstein*, Q. Bertrand*, A. Gramfort, J. Salmon, S. Vaiter, Model identification and local linear convergence of coordinate descent, Optimization Letters

• 2022

  • D. Scieur, Q. Bertrand, G. Gidel, F. Pedregosa, The Curse of Unrolling: Rate of Differentiating Through Optimization, NeurIPS 2022

  • Q. Bertrand, Q. Klopfenstein, P.-A. Bannier, G. Gidel, M. Massias Beyond L1: Faster and Better Sparse Models with skglm, NeurIPS 2022 code, doc

  • Q. Bertrand*, Q. Klopfenstein*, M. Massias, M. Blondel, S. Vaiter, A. Gramfort, J. Salmon, Implicit differentiation for fast hyperparameter selection in non-smooth convex learning, JMLR, code, doc

• 2021

  • P.-A. Bannier, Q. Bertrand, J. Salmon, A. Gramfort, Electromagnetic neural source imaging under sparsity constraints with SURE-based hyperparameter tuning, Workshop medical imaging meets NeurIPS, NeurIPS2021, code

  • Q. Bertrand, M. Massias, Anderson acceleration of coordinate descent, AISTATS 2021, code, doc

• 2020

  • Q. Bertrand*, Q. Klopfenstein*, M. Blondel, S. Vaiter, A. Gramfort, J. Salmon, Implicit differentiation of Lasso-type models for hyperparameter optimization, ICML 2020, proc., code, doc

  • M. Massias*, Q. Bertrand*, A. Gramfort, J. Salmon, Support recovery and sup-norm convergence rates for sparse pivotal estimation, AISTATS 2020, proc.

• 2019

  • Q. Bertrand*, M. Massias*, A. Gramfort, J. Salmon, Handling correlated and repeated measurements with the smoothed multivariate square-root Lasso, NeurIPS 2019, proc., code, doc

Ph. D. Thesis

• Q. Bertrand, Hyperparameter selection for high dimensional sparse learning: application to neuroimaging, slides, recording of the defense

Slides

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

• Hyperparameter selection for high dimensional sparse learning: application to neuroimaging, 28/09/2021, Ph. D. Defense, Paris-Saclay, France.

• Anderson acceleration of coordinate descent, 07/06/2021, Journées des statistiques, Nice, France.

• Optimization for machine learning, “Hands on”, 04/01/2021, Data Science Summer School of École polytechnique, France.

• Implicit differentiation of Lasso-type models for hyperparameter optimization, 09/09/2020, SMAI MODE 2020, France.

Reviewing service

• ICML 2021-2025

• ICLR 2021-2025

• NeurIPS 2020-2025 (top reviewer in 2021 and 2022)

• JMLR 2021-2025

• TMLR 2023-2025