Mathurin Massias
Publications
Publications
|
|
Convexity in ReLU Neural Networks: beyond ICNNs?Journal of Mathematical Imaging and Vision, 2025, 67 (4), pp.40. ⟨10.1007/s10851-025-01253-x⟩ |
|
|
DeepInverse: A Python package for solving imaging inverse problems with deep learningJournal of Open Source Software, 2025, 10 (115), pp.8923. ⟨10.21105/joss.08923⟩ |
|
|
Iterative regularization for low complexity regularizersNumerische Mathematik, 2024, 156 (2), pp.641-689. ⟨10.1007/s00211-023-01390-8⟩ |
|
|
Implicit differentiation for fast hyperparameter selection in non-smooth convex learningJournal of Machine Learning Research, 2022, 23 (1), pp.6680 - 6722 |
|
|
Dual Extrapolation for Sparse Generalized Linear ModelsJournal of Machine Learning Research, 2020, 21 (234), pp.1-33 |
|
|
How to improve expressivity of convex ReLU neural networks?GRETSI 2025 - XXXème Colloque Francophone de Traitement du Signal et des Images, Aug 2025, Strasbourg, France |
|
|
Schur's Positive-Definite Network: Deep Learning in the SPD cone with structureInternational Conference on Learning Representations ICLR 2025, Apr 2025, Singapore, Singapore |
|
|
On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target StochasticityNeurIPS 2025 - 39th Annual Conference on Neural Information Processing Systems, Dec 2025, San Diego (CA), United States |
|
|
En quête de précision : Un benchmark open-source et un solveur polyvalent pour le Graphical LassoGRETSI 2025 - XXXème Colloque Francophone de Traitement du Signal et des Images, Aug 2025, Strasboug, France. pp.1-3 |
|
|
Implicit Differentiation for Hyperparameter Tuning the Weighted Graphical LassoGRETSI 2023 - XXIXème Colloque Francophone de Traitement du Signal et des Images, Aug 2023, Grenoble (France), France. pp.1-4 |
|
|
Coordinate Descent for SLOPE26th International Conference on Artificial Intelligence and Statistics - AISTATS 2023, Apr 2023, Valencia, Spain |
|
|
Dimension-free convergence rates for gradient Langevin dynamics in RKHSCOLT 2022 - 35th Annual Conference on Learning Theory, Jul 2022, London, United Kingdom |
|
|
Beyond L1: Faster and Better Sparse Models with skglm36th Conference on Neural Information Processing Systems (NeurIPS 2022), Nov 2022, New Orleans, United States |
|
|
Benchopt: Reproducible, efficient and collaborative optimization benchmarksNeurIPS 2022 - 36. Conference on Neural Information Processing Systems, Nov 2022, La Nouvelle Orléans, United States |
|
|
Anderson acceleration of coordinate descentAISTATS 2021, Apr 2021, San Diego / Virtual, United States |
|
|
Iterative regularization for convex regularizersAISTATS 2021, Apr 2021, San Diego / Virtual, United States |
|
|
Support recovery and sup-norm convergence rates for sparse pivotal estimationAISTATS2020, Aug 2020, Virtual, Italy |
|
|
Exploiting regularity in sparse Generalized Linear ModelsSPARS 2019 - Signal Processing with Adaptive Sparse Structured Representations, Jul 2019, Toulouse, France |
|
|
Handling correlated and repeated measurements with the smoothed multivariate square-root LassoNeurIPS 2019, Dec 2019, Vancouver, Canada |
|
|
Learning step sizes for unfolded sparse codingNeurIPS 2019 - Advances in Neural Information Processing Systems, Dec 2019, Vancouver, Canada |
|
|
Celer: a Fast Solver for the Lasso with Dual ExtrapolationICML 2018 - 35th International Conference on Machine Learning, Jul 2018, Stockholm, Sweden. pp.3321-3330 |
|
|
Generalized Concomitant Multi-Task Lasso for Sparse Multimodal Regression21st International Conference on Artificial Intelligence and Statistics (AISTATS 2018), Apr 2018, Lanzarote, Spain |
A Visual Dive into Conditional Flow Matching2025 |
|
|
The Generation Phases of Flow Matching: a Denoising Perspective2026 |
|
|
Proximal Operators of Sorted Nonconvex Penalties2025 |
|
|
Sparse high dimensional regression in the presence of colored heteroscedastic noise : application to M/EEG source imagingStatistics [math.ST]. Université Paris Saclay (COmUE), 2019. English. ⟨NNT : 2019SACLT053⟩ |
|
|
Sparse high dimensional regression in the presence of colored heteroscedastic noise: application to M/EEG source imagingMachine Learning [stat.ML]. Telecom Paristech, 2019. English. ⟨NNT : ⟩ |
skglmLogiciel hal-05051525v1 |
|
BenchoptLogiciel hal-05051515v1 |